v1.2.0

What's Changed

• Add pre-download sweep support by @alan-cooney in #154

Full Changelog: v1.1.0...v1.2.0

v1.1.0

What's Changed

• Update vscode settings for latest vscode release by @alan-cooney in #149
• Support text datasets with sweep by @alan-cooney in #151
• Add multiprocessing support to datasets by @alan-cooney in #150
• Add wandb save by @alan-cooney in #153

Full Changelog: v1.0.1...v1.1.0

v1.0.1

What's Changed

• Add colab link for pre-processing datasets by @alan-cooney in #145
• Add more pipeline tests by @alan-cooney in #146
• Fix the pre-process demo dataset links by @alan-cooney in #147
• Improve pipeline test coverage by @alan-cooney in #148

Full Changelog: v1.0.0...v1.0.1

v1.0.0

What's Changed

• Fix the validation dataset size by @alan-cooney in #144

Full Changelog: v0.19.0...v1.0.0

v0.19.0

What's Changed

• Add pre-processed and pre-downloaded datasets support by @alan-cooney in #143
• Make the demo notebook more visible in the README by @ArthurConmy in #142

Full Changelog: v0.18.0...v0.19.0

v0.18.0

What's Changed

• Clean demo output by @alan-cooney in #134
• Add multiple neuron activity log thresholds by @alan-cooney in #135
• Add categorisation to all wandb metrics by @alan-cooney in #136
• Fix the neuron resampler approach by @alan-cooney in #141

Full Changelog: v0.17.0...v0.18.0

v0.17.0

What's Changed

• Fix colab install by @alan-cooney in #132
• Add wandb sweep helper by @alan-cooney in #133

Full Changelog: v0.16.0...v0.17.0

v0.16.0

What's Changed

• Old mock dataset removal by @bryce13950 in #125
• Improve links in docs by @alan-cooney in #124
• Remove deprecated extension by @alan-cooney in #126
• Disable import auto completions by @alan-cooney in #128
• Unified resample merge by @HoagyC in #123
• Default L2 loss to mean across features dimension by @alan-cooney in #129
• Move axis names to be used directly by @alan-cooney in #130
• Fix demo by @alan-cooney in #131

Full Changelog: v0.15.0...v0.16.0

v0.15.0

What's Changed

• Remove tokenizers pin by @ArthurConmy in #116
• Validation and Checkpoint Intervals by @efarrell1 in #117
• Add data generation pipeline tests by @alan-cooney in #118
• Fix the linear encoder's initialisation by @alan-cooney in #121
• Fix loss reducer type signature by @alan-cooney in #120
• Add toml extension to recommended extensions by @alan-cooney in #119
• Add tests against Neel's implementation by @alan-cooney in #122

New Contributors

• @efarrell1 made their first contribution in #117

Full Changelog: v0.14.0...v0.15.0

v0.14.0

What's Changed

• Add learned activations L0 norm metric by @lucyfarnik in #91
• Refactor pipeline and abstract pipeline to be a single class by @bryce13950 in #113

New Contributors

• @lucyfarnik made their first contribution in #91

Full Changelog: v0.13.0...v0.14.0