Which Attention Heads are like the Human Head? Not the Ones that Compute
Alignment and causation dissociate: brain-aligned heads contribute to performance, but their removal is substantially less disruptive than removal of heads selected via attribution patching, and FV-ranked removal is substantially more disruptive than brain-ranked removal.
Christopher Pinier, Gustaw Opielka, Hannes Rosenbusch et al.
· 0 citations