Attention heads in GPT-2 and Pythia-6.9B that promote factual output act by general copy suppression rather than selective counterfactual suppression, with domain-dependent effects that sharpen in larger models.
Pythia: A suite for analyzing large language models across training and scaling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
Attention heads in GPT-2 and Pythia-6.9B that promote factual output act by general copy suppression rather than selective counterfactual suppression, with domain-dependent effects that sharpen in larger models.