finding
active
finding:tuned-lens-skips-to-output-answers-and-is-best-next-token-predictor-while-j-lens-has-highest-klTuned lens skips to output answers and is best next-token predictor while J-lens has highest KL.
Comparison.
Source paper
extracted_fromAuthors
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Methods comparison.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Methodological comparison.
- Implicit modulation.
- Model organism results.
- Automated auditing.
- Related work.
- Mechanistic proof of concept.
- Imagine instruction raises property name in J-lens while J-orthogonalized property probe stays at baseline.finding0.785J-space privileged.
- Mediation control.