Towards Monosemanticity: Decomposing Language Models With Dictionary Learning
Bricken et al., 2023, Towards Monosemanticity (Transformer Circuits Thread)
Subscriber deck — free during early access
1 cards in “Sparse Autoencoder Setup” · whole deck
Sparse Autoencoder Setup
- How was the sparse autoencoder trained, and what practical tricks mattered?To reconstruct MLP activations with an MSE loss plus an L1 penalty on feature activations, using Adam. Lots of data made features sharper, and periodically resampling “dead” features (ones that stopped firing) to fit poorly reconstructed examples let more features be learned.
- Bricken et al., 2023, Towards Monosemanticity (Transformer Circuits Thread), Sparse Autoencoder Setup
Source
- Trenton Bricken, Adly Templeton, Joshua Batson, Brian Chen, Adam Jermyn, Tom Conerly, Nicholas L. Turner, Cem Anil, Carson Denison, Amanda Askell, Robert Lasenby, Yifan Wu, Shauna Kravec, Nicholas Schiefer, Tim Maxwell, Nicholas Joseph, Zac Hatfield-Dodds, Alex Tamkin, Karina Nguyen, Brayden McLean, Josiah E. Burke, Tristan Hume, Shan Carter, Tom Henighan and Chris Olah. 2023. Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. In Transformer Circuits Thread. https://transformer-circuits.pub/2023/monosemantic-features/index.html