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 “"Finite State Automata"” · whole deck
"Finite State Automata"
- What are feature “finite-state automata”?Chains in which one feature raises the probability of certain tokens, which then make another feature fire at the next step, and so on; such assemblies implement behaviours like producing valid HTML, although the model didn’t learn them as deliberate circuits.
- Bricken et al., 2023, Towards Monosemanticity (Transformer Circuits Thread), "Finite State Automata"
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