Skip to yearly menu bar Skip to main content

Workshop: Attributing Model Behavior at Scale (ATTRIB)

Copy Suppression: Comprehensively Understanding an Attention Head

Callum McDougall · Arthur Conmy · Cody Rushing · Tom McGrath · Neel Nanda


We present a single attention head in GPT-2 Small that has one main role across the entire training distribution. If components in earlier layers predict a certain token, and this token appears earlier in the context, the head suppresses it: we call this copy suppression. Attention Head 10.7 (L10H7) suppresses naive copying be5 havior which improves overall model calibration. This explains why multiple prior works studying certain narrow tasks found negative heads that systematically favored the wrong answer. We uncover the mechanism that the Negative Heads use for copy suppression with weights-based evidence and are able to explain 76.9% of the impact of L10H7 in GPT-2 Small. To the best of our knowledge, this is the most comprehensive description of the complete role of a component in a language model to date. Interactive visualizations of the copy suppression phenomena may be seen at our web app

Chat is not available.