Search Results for author: Callum McDougall

Found 1 papers, 1 papers with code

Copy Suppression: Comprehensively Understanding an Attention Head

1 code implementation6 Oct 2023 Callum McDougall, Arthur Conmy, Cody Rushing, Thomas McGrath, Neel Nanda

We show that self-repair is implemented by several mechanisms, one of which is copy suppression, which explains 39% of the behavior in a narrow task.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.