←back to thread

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

(transformer-circuits.pub)
168 points 1wheel | 1 comments | 21 May 24 15:15 UTC | HN request time: 0.206s | source
Show context
tantalor ◴[21 May 24 16:33 UTC] No.40430626[source]▶
I always assumed the way to map these models would be by ablation, the same way we map the animal brain.

Damage part X of the network and see what happens. If the subject loses the ability to do Y, then X is responsible for Y.

See https://en.wikipedia.org/wiki/Phineas_Gage

replies(1): >>40431756 #
1. rmorey ◴[21 May 24 18:09 UTC] No.40431756[source]▶
We are so far ahead in the case of these models - we already have the complete wiring diagram! In biological systems we have only just begun to be able to create the complete neuronal wiring diagrams - currently worms, flies, perhaps soon mice