Transformer-lens

New models! This release adds support for Gemma 2 2B as well as Qwen2. This also removes official support for python 3.8. Python 3.8 should continue to work for a while, but there is a high risk that it will be unstable past this release. If you need python 3.8, try locking to this release or any previous release.

What's Changed
* Fix typo in `embed.py` docs by ArthurConmy in https://github.com/TransformerLensOrg/TransformerLens/pull/677
* Move the HookedSAE / HookedSAETransformer warning to a less prominent… by ArthurConmy in https://github.com/TransformerLensOrg/TransformerLens/pull/676
* NamesFilter can be a string by jettjaniak in https://github.com/TransformerLensOrg/TransformerLens/pull/679
* Adding RMSNorm to apply_ln_to_stack by gaabrielfranco in https://github.com/TransformerLensOrg/TransformerLens/pull/663
* added arena content as a notebook by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/674
* Test arena cleanup by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/681
* docs: update Main_Demo.ipynb by eltociear in https://github.com/TransformerLensOrg/TransformerLens/pull/658
* Add support for Qwen2 models by g-w1 in https://github.com/TransformerLensOrg/TransformerLens/pull/662
* Added gemma-2 2b by curt-tigges in https://github.com/TransformerLensOrg/TransformerLens/pull/687
* Python 3.8 removal by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/690
* 2.3.0 by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/688

New Contributors
* gaabrielfranco made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/663
* eltociear made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/658
* g-w1 made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/662
* curt-tigges made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/687

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.2.2...v2.3.0

Quick little bug fix!

What's Changed
* Fix attention result projection by callummcdougall in https://github.com/TransformerLensOrg/TransformerLens/pull/666
* fix: fixing broken backward hooks change by chanind in https://github.com/TransformerLensOrg/TransformerLens/pull/673


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.2.1...v2.2.2

Quick little bug fix in the Abstract Attention component shape.

What's Changed
* Fix attention result projection by callummcdougall in https://github.com/TransformerLensOrg/TransformerLens/pull/666


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.2.0...v2.2.1

New Contributors
* ianand made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/636
* FlyingPumba made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/643

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.1.0...v2.2.0

Here's an important one! This release adds Gemma-2, and it also greatly improves model accuracy across the board. It is highly recommended that everyone update to this version immediately to take advantage of these accuracy improvements.

What's Changed
* Fix typo in Main_Demo.ipynb by ianand in https://github.com/TransformerLensOrg/TransformerLens/pull/636
* Add comparing-to-huggingface.ipynb. by joelburget in https://github.com/TransformerLensOrg/TransformerLens/pull/637
* Add tests for gated mlp by anthonyduong9 in https://github.com/TransformerLensOrg/TransformerLens/pull/638
* Match Huggingface MLP implementation exactly. by joelburget in https://github.com/TransformerLensOrg/TransformerLens/pull/641
* Add tests for ActivationCache by FlyingPumba in https://github.com/TransformerLensOrg/TransformerLens/pull/643
* Moved mixtral weights to another module by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/646
* Fixed weight conversion by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/648
* Move out pretrained weight conversions by richardkronick in https://github.com/TransformerLensOrg/TransformerLens/pull/647
* Match Huggingface GPT2 implementation *exactly* by joelburget in https://github.com/TransformerLensOrg/TransformerLens/pull/645
* Fix Out bias not being summed in attention component when using 4 bit precision by FlyingPumba in https://github.com/TransformerLensOrg/TransformerLens/pull/654
* Mlp cleanup by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/652
* Added support for Gemma-2 by neelnanda-io in https://github.com/TransformerLensOrg/TransformerLens/pull/650
* add tests for Attention by anthonyduong9 in https://github.com/TransformerLensOrg/TransformerLens/pull/639

New model support, and a handful of bug fixes to documentation!

What's Changed
* Encoder-Decoder (T5) support by somvy in https://github.com/TransformerLensOrg/TransformerLens/pull/605
* Update README links to ARENA mech interp tutorials by gileshd in https://github.com/TransformerLensOrg/TransformerLens/pull/630
* Lock datasets version by courtney-sims in https://github.com/TransformerLensOrg/TransformerLens/pull/632

New Contributors
* somvy made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/605
* gileshd made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/630
* courtney-sims made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/632

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.0.1...v2.1.0