Standard tests for mechanistic roles in transformer attention heads are insufficient because heads that pass them fail to transfer computations across prompts under matched controls.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers
Standard tests for mechanistic roles in transformer attention heads are insufficient because heads that pass them fail to transfer computations across prompts under matched controls.