Mechanistic interpretability papers substitute validation metrics for causal identification without stating assumptions, and the authors propose a disclosure norm requiring explicit identification strategies.
Towards monosemanticity: decomposing language models with dictionary learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
Mechanistic interpretability papers substitute validation metrics for causal identification without stating assumptions, and the authors propose a disclosure norm requiring explicit identification strategies.