AIBearisharXiv – CS AI · 18h ago7/10
🧠
Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers
Researchers demonstrate that attention heads in large language models passing standard mechanistic interpretability tests—necessity, linear encoding, and ablation recovery—fail to transfer their computations to different contexts. The study introduces KID framework and a three-stage validation pipeline, revealing that many claimed attention head roles are artifacts of specific prompt contexts rather than genuine semantic functions.