Gemma Scope

Open Sparse Autoencoders Everywhere All At Once on Gemma 2

discuss: https://t.co/hLAdvC1FJC

Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features.… pic.twitter.com/aXO8Ihm6Tv

— AK (@_akhaliq) 12 août 2024

Gemma Scope Open Sparse Autoencoders Everywhere All At Once on Gemma 2 discuss: https://
huggingface.co/papers/2408.05
147
… Sparse autoencoders (SAEs) are an unsupervised method for learning a sparse decomposition of a neural network's latent representations into seemingly interpretable features.

→ View original post on X — @_akhaliq