Transformer-lens

Nice little release! This release adds a new parameter named `first_n_layers` that will allow you to specify how many layers of a model you want to load.

What's Changed
* Fix typo in bug issue template by JasonGross in https://github.com/TransformerLensOrg/TransformerLens/pull/715
* HookedTransformerConfig docs string: `weight_init_mode` => `init_mode` by JasonGross in https://github.com/TransformerLensOrg/TransformerLens/pull/716
* Allow loading only first n layers. by joelburget in https://github.com/TransformerLensOrg/TransformerLens/pull/717


**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.4.1...v2.5.0

Little update to the code usage, but huge update for memory consumption! TransformerLens now needs almost half the memory it needed previously to boot thanks to a change with how the TransformerLens models are loaded.

What's Changed
* removed einsum causing error when use_atten_result is enabled by oliveradk in https://github.com/TransformerLensOrg/TransformerLens/pull/660
* revised loading to recycle state dict by bryce13950 in https://github.com/TransformerLensOrg/TransformerLens/pull/706

New Contributors
* oliveradk made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/660

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.4.0...v2.4.1

Nice little update! This gives users a little bit more control over attention masks, as well as adds a new demo.

What's Changed
* Improve attention masking by UFO-101 in https://github.com/TransformerLensOrg/TransformerLens/pull/699
* add a demo for Patchscopes and Generation with Patching by HenryCai11 in https://github.com/TransformerLensOrg/TransformerLens/pull/692

New Contributors
* HenryCai11 made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/692

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.3.1...v2.4.0

New Contributors
* mntss made their first contribution in https://github.com/TransformerLensOrg/TransformerLens/pull/694

**Full Changelog**: https://github.com/TransformerLensOrg/TransformerLens/compare/v2.3.0...v2.3.1

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