Posts

Mechanistic Interpretability of Llama 3.2 with Sparse Autoencoders 2024-11-24T05:45:20.124Z

Comments

Comment by PaulPauls on Mechanistic Interpretability of Llama 3.2 with Sparse Autoencoders · 2024-11-24T19:38:31.824Z · LW · GW

Hi Neel,

you're absolutely right, all research in the gemmascope paper was performed on the open source Gemma 2 model. I wanted to group up all research that my paper was based on in a concise sentence and by doing so erroneously put you in the 'proprietary LLMs' section. I went ahead and corrected the mistake.

My apologies.

I hope you still enjoyed the project and thank you for your great research work at DeepMind. =)