finding
active
finding:with-pt-only-semantic-search-present-adding-interpretability-tools-gives-smaller-additional-benefit

With PT-only semantic search present, adding interpretability tools gives smaller additional benefit

Interp value partly from surfacing PT data.

Source paper

extracted_from
Building and evaluating alignment auditing agents
(2025) · Trenton Bricken · Rowan Wang · Sam Bowman

Neighborhood — ranked by edge-count