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 “How Interpretable is the Typical Feature?” · whole deck
How Interpretable is the Typical Feature?
- How did the interpretability of features compare with neurons?A blinded human rater gave the median neuron 0 on the rubric (no hypothesis at all) and the median feature interval 12 (confident, consistent, matching the logits). Automated interpretability with Claude agreed: predicted activations correlated far better for features, and logit predictions were 74% vs 58% accurate.
- Bricken et al., 2023, Towards Monosemanticity (Transformer Circuits Thread), How Interpretable is the Typical Feature?
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