Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Templeton et al., 2024, Scaling Monosemanticity (Transformer Circuits Thread)
Subscriber deck — free during early access
1 cards in “Sophisticated Features” · whole deck
Sophisticated Features
- What did the code-error and addition features show about the depth of features?A code-error feature fired on many kinds of bugs and, when clamped, made the model hallucinate error messages for correct code; an addition feature fired on functions that add numbers, even through function composition, and clamping it made the model think it was asked to execute an addition.
- Templeton et al., 2024, Scaling Monosemanticity (Transformer Circuits Thread), Sophisticated Features
Source
- Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L. Turner, Callum McDougall, Monte MacDiarmid, Alex Tamkin, Esin Durmus, Tristan Hume, Francesco Mosconi, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah and Tom Henighan. 2024. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet. In Transformer Circuits Thread. https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html