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 “Comparison to Other Approaches” · whole deck
Comparison to Other Approaches
- What advantages does dictionary learning have over linear probes for finding directions?It is a one-time cost producing millions of features, after which finding a relevant one needs only a few prompts, whereas probes need a bespoke dataset per concept; and being unsupervised, it can reveal unanticipated abstractions. Few-shot probe directions were neither interpretable nor effective for steering.
- Templeton et al., 2024, Scaling Monosemanticity (Transformer Circuits Thread), Comparison to Other Approaches
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