- fix: Merge pull request #33 from jbloomAus/fix/topk-selection-purview
Fix/topk selection purview (afccd5a
)
-
Update README.md (
8235a9e
) -
updated formatting/typing (
fb141ae
) -
Merge pull request #32 from jbloomAus/docs/readme-update
docs: updated readme (b5e5480
)
- TopK will now select from all latents regardless of feature batch size (
c1f0e14
)
- fix: update cached_activations directory to include number of prompts (
0308cb1
)
- fix: lint (
3fc0e2c
)
-
Merge branch 'main' of https://github.com/jbloomAus/SAEDashboard (
8f74a96
) -
Fix: divide by zero, cached_activations folder name (
1792298
)
- fix: update saelens to v4 (
ef1a330
)
- Merge branch 'main' of https://github.com/jbloomAus/SAEDashboard (
508a74d
)
- feat: np sae id suffix (
448b14e
)
-
Update README.md (
a1546fd
) -
Removed outdated vis type (
b0676af
) -
Update README.md (
9b8446a
) -
Updated format (
90e4a09
) -
Updated readme (
f6819a6
) -
Merge pull request #31 from jbloomAus/fix/reduce-mem
fix: added mem cleanup (60bd716
)
-
Fixed formatting (
f1fab0c
) -
Added cleanup (
305c46d
) -
Merge pull request #30 from jbloomAus/feat-mask-via-position
feat: prepending/appending tokens for prompt template + feat mask via Position (4c60e4c
)
-
add a few tests (
96247d5
) -
handle prefixes / suffixes and ignored positions (
bff7fd9
) -
simplify masking (
385b6e1
) -
add option for ignoring tokens at particular positions (
ed3426d
) -
Merge pull request #29 from jbloomAus/refactor/optimize-dfa-speed
Sped up DFA calculation 60x (f992e3c
)
-
Sped up DFA calculation (
be11cd5
) -
Added test to check for decoder weight dist (head dist) (
f147696
) -
Merge pull request #28 from jbloomAus/feature/np-topk-size-arg
Feature/np topk size arg (c5c1365
)
- Merge pull request #25 from jbloomAus/fix/dfa-for-gqa
Fix/dfa for gqa (85c345f
)
-
Fixed formatting (
48a67c7
) -
Removed redundant code from rebase (
a71fb9d
) -
fixed rebase (
57ee280
) -
Added tests for DFA for GQA (
fcfac37
) -
Removed duplicate code (
cc00944
) -
Fixed formatting (
50b08b4
) -
Removed debugging statements (
f7b949b
) -
more debug prints x3 (
53536b0
) -
more debug prints x2 (
6f2c504
) -
more debug prints (
e1bef90
) -
temp print statements (
fd75714
) -
updated ignore (
c01062f
) -
Reduced memory load of GQA DFA (
1ae40e9
) -
DFA will now work for models with grouped query attention (
c66c90f
) -
Edited default chunk size (
3c78bdc
) -
Fixed formatting (
10a36e3
) -
Removed debugging statements and added device changes (
0f51dd9
) -
more debug prints x3 (
112ef42
) -
more debug prints x2 (
ef154d6
) -
more debug prints (
1b18d14
) -
temp print statements (
2194d2c
) -
Lowered default threshold (
a49d1e5
) -
updated ignore (
2067655
) -
Reduced memory load of GQA DFA (
8ec1956
) -
DFA will now work for models with grouped query attention (
8f3cf55
) -
Added head attr weights functionality for when DFA is use (
234ea32
) -
Added tests for DFA for GQA (
3b99e36
) -
Simply updated default value for top K (
5c855fe
) -
Testing variable topk sizes (
79fe14b
) -
Merge pull request #27 from jbloomAus/fix/resolve-duplication
Removed sources of duplicate sequences (525bffe
)
-
Updated location of wandb finish() (
921da77
) -
Added two sets of tests for duplication checks (
3e95ffd
) -
Restored original random indices function as it seemed ok (
388719b
) -
Removed sources of duplicate sequences (
853306c
) -
Removed duplicate code (
7093773
) -
More rebasing stuff (
59c6cd8
) -
Edited default chunk size (
7d68f9e
) -
Fixed formatting (
4d5f38b
) -
Removed debugging statements and added device changes (
76e17c9
) -
more debug prints x3 (
06535d3
) -
more debug prints x2 (
26e8297
) -
more debug prints (
9ded356
) -
temp print statements (
024ad57
) -
Lowered default threshold (
a3b5977
) -
updated ignore (
d5d325a
) -
Reduced memory load of GQA DFA (
93eb1a9
) -
DFA will now work for models with grouped query attention (
6594155
) -
Added head attr weights functionality for when DFA is use (
9312d90
)
- fix: multi-gpu-tlens
fix: handle multiple tlens devices (ed1e967
)
- fix: handle multiple tlens devices (
ba5368f
)
-
Fixed formatting (
ed7d3b1
) -
Removed debugging statements (
6489d1c
) -
more debug prints x3 (
5ba2b8a
) -
more debug prints x2 (
e124ff9
) -
more debug prints (
e2b0c35
) -
temp print statements (
95df55b
) -
Lowered default threshold (
dc1f31a
) -
updated ignore (
eb0d56a
) -
Reduced memory load of GQA DFA (
05867f1
) -
DFA will now work for models with grouped query attention (
91a5dd1
) -
Added head attr weights functionality for when DFA is use (
03a615f
)
- feat: accelerate caching. Torch load / save faster when files are small.
Refactor/accelerate caching (6027d0a
)
-
Updated formatting (
c1ea288
) -
Sped up caching with native torch functions (
230840a
) -
Increased cache loading speed (
83fe5f4
)
- feat: Refactor json writer and trigger DFA release
JSON writer has been refactored for reusability and readability (664f487
)
- Merge pull request #20 from jbloomAus/feature/dfa
SAEVisRunner DFA Implementation (926ea87
)
-
Refactored JSON creation from the neuronpedia runner (
d6bb24b
) -
Update ci.yaml (
4b2807d
) -
Fixed formatting (
a62cc8f
) -
Fixed target index (
ca2668d
) -
Corrected DFA indexing (
d5028ae
) -
Adding temporary testing notebook (
98e4b2f
) -
Added DFA output to neuronpedia runner (
68eeff3
) -
Fixed test typehints (
d358e6f
) -
Fixed formatting (
5cb19e2
) -
Corrected typehints (
6173fbd
) -
Removed another unused import (
8be1572
) -
Removed unused imports (
9071210
) -
Added support for DFA calculations up to SAE Vis runner (
4a08ffd
) -
Added activation collection flow for DFA (
0ebb1f3
) -
Merge pull request #19 from jbloomAus/fix/remove_precision_reduction
Removed precision reduction option (a5f8df1
)
-
Removed float16 option entirely from quantile calc (
1b6a4a9
) -
Removed precision reduction option (
cd03ffb
)
- feat: seperate files per dashboard html (
cd8d050
)
- Merge pull request #17 from jbloomAus/refactor/remove_enc_b
Removed all encoder B code (67c9c3f
)
- Merge pull request #18 from jbloomAus/feat-seperate-files-per-html-dashboard
feat: seperate files per dashboard html (8ff69ba
)
-
Removed all encoder B code (
5174e2e
) -
Merge pull request #16 from jbloomAus/performance_refactor
Create() will now reduce precision by default (fb07b90
)
-
Removed line (
d795490
) -
Removed unnecessary print (
4544f86
) -
Precision will now be reduced by default for quantile calc (
539d222
) -
Merge pull request #15 from jbloomAus/quantile_efficiency
Quantile OOM prevention (4a40c37
)
-
Made quantile batch optional and removed sampling code (
2df51d3
) -
Added device check for test (
afbb960
) -
Added parameter for quantile calculation batching (
49d0a7a
) -
Added type annotation (
c71c4aa
) -
Removed unused imports (
ec01bfe
) -
Added float16 version of quantile calculation (
2f01eb8
) -
Merge pull request #13 from jbloomAus/hook_z_support
fix: restore hook_z support following regression. (ea87559
)
-
format (
21e3617
) -
make sure hook_z works (
efaeec0
) -
Merge pull request #12 from jbloomAus/use_sae_lens_loading
Use sae lens loading (89bba3e
)
-
add settings.json (
d8f3034
) -
add dtype (
0d8008a
) -
cli util (
9da440e
) -
wandb logging improvement (
a077369
) -
add override for np set name (
8906d10
) -
auto add folder path to output dir (
35e06ab
) -
update tests (
50163b0
) -
first step towards sae_lens remote loading (
415a2d1
)
- fix: neuronpedia uses api_key for uploading features, and update sae_id->sae_set (
0336a35
)
- Merge pull request #11 from jbloomAus/ignore_bos_option
Ignore bos option (ae34b70
)
-
change threshold (
4a0be67
) -
type fix (
525b6a1
) -
default ignore bos eos pad (
d2396a7
) -
ignore bos tokens (
96cf6e9
) -
jump relu support in feature masking context (
a1ba87a
) -
depend on latest sae lens (
4988207
) -
Merge pull request #10 from jbloomAus/auth_and_sae_set
fix: neuronpedia uses api_key for uploading features, and update sae_id -> sae_set (4684aca
)
-
Combine upload-features and upload-dead-stubs (
faac839
) -
Activation store device should be cuda when available (
93050b1
) -
Activation store device should be cuda when available (
4469066
) -
Better support for huggingface dataset path (
3dc4b78
) -
Docker tweak (
a1a70cb
)
- fix: don't sample too many tokens + other fixes
fix: don't sample too many tokens (b2554b0
)
- fix: don't sample too many tokens (
0cbb2ed
)
-
- Don't force manual overrides for dtype - default to SAE's dtype
- Add n_prompts_in_forward_pass to neuronpedia.py
- Add n_prompts_total, n_tokens_in_prompt, and dataset to neuronpedia artifact
- Remove NPDashboardSettings for now (just save the NPRunnerConfig later)
- Fix lint error
- Consolidate minibatch_size_features/tokens to n_feats_at_a_time and n_prompts_in_fwd_pass
- Update/Fix NP acceptance test (
b6282c8
)
- Merge pull request #7 from jbloomAus/performance-improvement
feat: performance improvement (f98b3dc
)
-
delete unused snapshots (
4210b48
) -
format (
de57a2d
) -
linter (
4725ffa
) -
hope flaky tests start passing (
8ac9e8e
) -
np.memmap caching and more explicit hyperparams (
9a24186
) -
Move docker" (
27b1a27
) -
Add docker to workflow (
a354fa4
) -
Dockerignore file (
ed9fcf3
) -
new versions (
f64e54d
) -
Add tools to docker image (
2a70f64
) -
Fix docker (
3805f20
) -
Fix docker image (
7f9ff2f
) -
Fix NP simple test, remove check for correlated neurons/features (
355fad5
) -
Dockerfile, small batching fix (
4df4c51
) -
set sae_device, activation_store device (
6d65b22
) -
Fix NP dtype error (
8bb4d9d
) -
format (
f667d92
) -
depend on latest sae_lens (
4a2a6a0
) -
use a much better method for getting subsets of feature activations (
7101f13
) -
add to gitignore (
20180e0
) -
add isort (
3ab0fda
)
- fix: trigger release (
87bf0b5
)
- Merge pull request #6 from jbloomAus/fix-bfloat16
fix bfloat 16 error (2f3c597
)
-
fix bfloat 16 error (
63c3c62
) -
Merge pull request #5 from jbloomAus/np-updates
Updates + fixes for Neuronpedia (9e6b5c4
)
-
Fix SAELens compatibility (
139e1a2
) -
Rename file (
16709ad
) -
Fix type (
6b20386
) -
Make Neuronpedia outputs an object, and add a real acceptance test (
a5db256
) -
Np Runner: Multi-gpu defaults (
07f7128
) -
Ensure minibatch is on correct device (
e206546
) -
NP Runner: Automatically use multi-gpu, devices (
bf280e6
) -
Allow dtype override (
a40077d
) -
NP-Runner: Remove unnecessary layer of batching. (
e2ac92b
) -
NP Runner: Allow skipping sparsity check (
ef74d2a
) -
Merge pull request #2 from jbloomAus/multiple-devices
feat: Multiple devices (535e6c9
)
- feat: experimental release 2 (
e264f97
)
- feat: experimental release (
d79310a
)
-
fix pyproject.toml (
a27c87d
) -
test deployment (
288a2d9
) -
refactor np runner and add acceptance test (
212593c
) -
Fix: Default context tokens length for neuronpedia runner (
aefe95c
) -
Allow custom context tokens length for Neuronpedia runner (
d204cc8
) -
Fix: Streaming default true (
1b91dff
) -
Fix n_devices error for non-cuda (
70b2dbd
) -
fix import path for ci (
3bd4687
) -
make pyright happy, start config (
b39ae85
) -
add black (
236855b
) -
fix ci (
12818d7
) -
add pytest cov (
aae0571
) -
bring checks in line with sae_lens (
7cd9679
) -
activation scaling factor (
333d377
) -
Move Neuronpedia runner to SAEDashboard (
4e691ea
) -
fold w_dec norm by default (
b6c9bc7
) -
rename sae_vis to sae_dashboard (
f0f5341
) -
rename feature data generator (
e02ed0a
) -
update demo (
8aa9e52
) -
add demo (
dd3036f
) -
delete old demo files (
3d86202
) -
remove unnecessary print statement (
9d3d937
) -
set sae lens version (
87a7691
) -
update older readme (
c5c98e5
) -
test (
923da42
) -
remove sae lens dep (
2c26d5f
) -
Merge branch 'refactor_b' (
3154d63
) -
pass linting (
0c079a1
) -
format (
6f37e2e
) -
run ci on all branches (
faa0cc4
) -
don't use feature ablations (
dc6e6dc
) -
mock information in sequences to make normal sequence generation pass (
c87b82f
) -
Remove resid (
ff83737
) -
adding a test for direct_effect_feature_ablation_experiment (
a9f3d1b
) -
shortcut direct_effect_feature_ablation_experiment if everything is zero (
2c68ff0
) -
fixing CI and replacing manual snapshots with syrupy snapshots (
3b97640
) -
more refactor, WIP (
81657c8
) -
continue refactor, make data generator (
eb1ae0f
) -
add use of safetensors cache for repeated calculations (
a241c32
) -
more refactor / benchmarking (
d65ee87
) -
only run unit tests (
5f11ddd
) -
fix lint issue (
24daf17
) -
format (
83e89ed
) -
organise tests, make sure only unit tests run on CI (
21f5fb1
) -
see if we can do some caching (
c1dca6f
) -
more refactoring (
b3f0f41
) -
further refactor, possible significant speed up (
ddd3496
) -
more refactor (
a5f6deb
) -
refactoring in progress (
d210b60
) -
use named arguments (
4a81053
) -
remove create method (
43b2018
) -
move chunk (
0f26aa8
) -
use fixtures (
7c11dd9
) -
refactor to create runner (
9202c19
) -
format (
abd8747
) -
target ci at this branch (
ea3b2a3
) -
comment out release process for now (
7084b5b
) -
test generated output (
7b8b2ab
) -
commit current demo html (
00a03a0
)
- fix: remove circular dep with sae lens (
1dd9f6c
)
- Merge pull request #44 from chanind/pytest-setup
chore: setting up pytest (034eefa
)
- Merge pull request #43 from callummcdougall/move_saelens_dep
Remove dependency on saelens from pyproject, add to demo.ipynb (147d87e
)
-
Add missing matplotlib (
572a3cc
) -
Remove dependency on saelens from pyproject, add to demo.ipynb (
1e6f3cf
) -
Merge branch 'main' of https://github.com/callummcdougall/sae_vis (
4e7a24c
) -
fix conflicts (
ea3d624
) -
Merge pull request #41 from callummcdougall/allow_disable_buffer
oops I forgot to switch back to main before pushing (1312cd0
)
-
Merge branch 'main' into allow_disable_buffer (
e7edf5a
) -
16 (
64e7018
) -
Merge pull request #40 from chanind/semantic-release-autodeploy
chore: setting up semantic-release for auto-deploy (a4d44d1
)
-
version 0.2.16 (
afca0be
) -
Merge pull request #38 from chanind/type-checking
Enabling type checking with Pyright (f1fd792
)
- Merge pull request #39 from callummcdougall/fix_loading_saelens_sae
FIX: SAELens new format has "scaling_factor" key, which causes assert to fail (983aee5
)
-
Fix Formatting (
13b8106
) -
Merge branch 'main' into fix_loading_saelens_sae (
21b0086
) -
Allow SAELens autoencoder keys to be superset of required keys, instead of exact match (
6852170
) -
enabling type checking with Pyright (
05d14ea
) -
Fix version (
5a43916
) -
format (
8f1506b
) -
v0.2.17 (
2bb14da
) -
Use main branch of SAELens (
2b34505
) -
Update version 0.2.16 (
bf90293
) -
Merge pull request #36 from callummcdougall/allow_disable_buffer
FEATURE: Allow setting buffer to None, which gives the whole activation sequence (f5f9594
)
-
fix all indices view (
5f87d52
) -
Merge pull request #35 from callummcdougall/fix_gpt2_demo
Fix usage of SAELens and demo notebook (88b5933
)
-
Merge branch 'fix_gpt2_demo' into allow_disable_buffer (
ea57bfc
) -
Import updated SAELens, use correct tokens, fix missing file cfg.json file error. (
14ba9b0
) -
Merge pull request #34 from ArthurConmy/patch-1
Update README.md (3faac82
)
-
Update README.md (
416eca8
) -
Merge pull request #33 from chanind/setup-poetry-and-ruff
Setting up poetry / ruff / github actions (287f30f
)
-
setting up poetry and ruff for linting/formatting (
0e0eba9
) -
fix feature vis demo gpt (
821781e
) -
Allow disabling the buffer (
c1be9f8
) -
add scatter plot support (
6eab28b
) -
update setup (
8d2ca53
) -
fix setup (
9cae8f4
) -
Merge branch 'main' of https://github.com/callummcdougall/sae_vis (
ed8f8cb
) -
fix sae bug (
247d14b
) -
Merge pull request #27 from wllgrnt/will-add-eindex-dependency
Update setup.py with eindex dependency (8d7ed12
)
- Merge pull request #32 from hijohnnylin/pin_older_sae_training
Demo notebook errors under "Multi-layer models" vis (9ac1dac
)
Without this, 'pip install sae-vis' will cause errors when e.g. you do 'from sae_vis.data_fetching_fns import get_feature_data' (a9d7de9
)
-
update version number (
72e584b
) -
add gifs to readme (
1393740
) -
test gif (
4fbafa6
) -
fix height issue (
3f272f6
) -
fix pypi (
7151164
) -
update setup (
8c43478
) -
Merge pull request #26 from hijohnnylin/update_html_anomalies
Update and add some HTML_ANOMALIES (1874a47
)
-
Update and add some HTML_ANOMALIES (
c541b7f
) -
0.2.9 (
a5c8a6d
) -
fix readme (
5a8a7e3
) -
include feature tables (
7c4c263
) -
add license (
fa02a3d
) -
Merge branch 'main' of https://github.com/callummcdougall/sae_vis (
ca5efcd
) -
re-fix html anomalies (
2fbae4c
) -
Merge pull request #24 from chanind/fix-pypi-repo-link
fixing repo URL in setup.py (14a0be5
)
-
fixing repo URL in setup.py (
4faeca5
) -
fix hook point bug (
9b573b2
) -
Merge pull request #20 from chanind/fix-final-resid-layer
fixing bug if hook_point == hook_point_resid_final (d6882e3
)
-
fixing bug using hook_point_resid_final (
cfe9b30
) -
fix indexing speed (
865ff64
) -
enable JSON saving (
feea47a
) -
Merge pull request #19 from chanind/support-mlp-and-attn-out
supporting mlp and attn out hooks (1c5463b
)
-
supporting mlp and attn out hooks (
a100e58
) -
Merge branch 'main' of https://github.com/callummcdougall/sae_vis (
083aeba
) -
fix variable naming (
2507918
) -
Merge pull request #18 from chanind/remove-build-artifacts
removing Python build artifacts and adding to .gitignore (b0e0594
)
-
removing Python build artifacts and adding to .gitignore (
b6486f5
) -
update readme (
0ee3608
) -
update readme (
f8351f8
) -
update version number (
1e74408
) -
fix formatting and docstrings (
b9fe2bb
) -
Merge pull request #17 from jordansauce/sae-agnostic-functions-new
Added SAE class agnostic functions (0039c6f
)
-
add to pypi (
02a5b9a
) -
Added sae class agnostic functions
Added parse_feature_data() and parse_prompt_data() (e2709d0
)
-
update notebook images (
b87ad4d
) -
fix layer parse and custom device (
14c7ae9
) -
update dropdown styling (
83be219
) -
add custom prompt vis (
cabdc5c
) -
d3 & multifeature refactor (
f79a919
) -
remove readme links (
4bcef48
) -
add demo html (
629c713
) -
remove demos (
beedea9
) -
fix quantile error (
3a23cfd
) -
width 425 (
f25c776
) -
fix device bug (
85dfa49
) -
dont return vocab dict (
b4c7138
) -
save as JSON, fix device (
eba2cff
) -
simple fixed and issues (
b28a0f7
) -
Merge pull request #8 from lucyfarnik/topk-empty-mask
Topk error handling for empty masks (2740c00
)
-
Topk error handling for empty masks (
1c2627e
) -
viz to vis (
216d02b
) -
update readme links (
f9b3f95
) -
update for TL (
1941db1
) -
Merge pull request #5 from lucyfarnik/transformer-lens-models
Compatibility with TransformerLens models (8d59c6c
)
-
Merge branch 'main' into transformer-lens-models (
73057d7
) -
Merge pull request #4 from lucyfarnik/resid-saes-support
Added support for residual-adjacent SAEs (b02e98b
)
- Merge pull request #7 from lucyfarnik/fix-histogram-div-zero
Fixed division by zero in histogram calculation (3aee20e
)
- Merge pull request #6 from lucyfarnik/handling-dead-features
Edge case handling for dead features (9e43c30
)
-
add features argument (
f24ef7e
) -
fix image link (
22c8734
) -
Merge pull request #1 from lucyfarnik/read-me-links-fix
Fixed readme links pointing to the old colab (86f8e20
)
-
Fixed division by zero in histogram calculation (
e986e90
) -
Added readme section about models (
7523e7f
) -
Fixed readme links pointing to the old colab (
28ef1cb
) -
Edge case handling for dead features (
5197aee
) -
Compatibility with TransformerLens models (
ba708e9
) -
Added support for MPS (
196c0a2
) -
Added support for residual-adjacent SAEs (
89aacf1
) -
black font (
d81e74d
) -
fix html bug (
265dedd
) -
add jax and dataset deps (
f1caeaf
) -
remove TL dependency (
155991f
) -
first commit (
7782eb6
)