PaulPauls

• PaulPaulsNov 24, 2024, 7:38 PM

  3 points

  0

  in reply to: Neel Nanda’s comment on: Mechanis­tic In­ter­pretabil­ity of Llama 3.2 with Sparse Autoencoders

  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. =)

Mechanis­tic In­ter­pretabil­ity of Llama 3.2 with Sparse Autoencoders