v2.3.0

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 #677
• Move the HookedSAE / HookedSAETransformer warning to a less prominent… by @ArthurConmy in #676
• NamesFilter can be a string by @jettjaniak in #679
• Adding RMSNorm to apply_ln_to_stack by @gaabrielfranco in #663
• added arena content as a notebook by @bryce13950 in #674
• Test arena cleanup by @bryce13950 in #681
• docs: update Main_Demo.ipynb by @eltociear in #658
• Add support for Qwen2 models by @g-w1 in #662
• Added gemma-2 2b by @curt-tigges in #687
• Python 3.8 removal by @bryce13950 in #690
• 2.3.0 by @bryce13950 in #688

New Contributors

• @gaabrielfranco made their first contribution in #663
• @eltociear made their first contribution in #658
• @g-w1 made their first contribution in #662
• @curt-tigges made their first contribution in #687

Full Changelog: v2.2.2...v2.3.0