AWhat changed
Built prompt-specific attribution graphs using cross-layer transcoders as an interpretable replacement for model MLP computation, with intervention and faithfulness checks.
Scientific scope
Built prompt-specific attribution graphs using cross-layer transcoders as an interpretable replacement for model MLP computation, with intervention and faithfulness checks. Attention patterns and normalization are frozen; reconstruction errors, missing attention circuits and incomplete mechanisms limit explanations. Graphs are not complete or globally faithful model proofs.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Attention patterns and normalization are frozen; reconstruction errors, missing attention circuits and incomplete mechanisms limit explanations. Graphs are not complete or globally faithful model proofs.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction