Attention-head functions can be inferred from parameters alone via vocabulary-space top-k scoring, and these inferences match head outputs and survive causal ablation across six LLMs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inferring Functionality of Attention Heads from their Parameters
Attention-head functions can be inferred from parameters alone via vocabulary-space top-k scoring, and these inferences match head outputs and survive causal ablation across six LLMs.