RSS

Francisco Ferreira da Silva

Karma: 35

Mech interp. Senior Fellow with Pivotal Research. ffsilva.io

Find­ing fea­tures in Trans­form­ers: Con­trastive di­rec­tions elicit stronger low-level per­tur­ba­tion re­sponses than baselines

Francisco Ferreira da Silva and StefanHex
20 Mar 2026 21:09 UTC
34 points
2 comments6 min readLW link