finding
active
finding:fisher-effectiveness-is-roughly-lognormal-across-10-orders-of-magnitude-median-is-10-000-below-maxFisher effectiveness is roughly lognormal across 10 orders of magnitude; median is 10,000× below max
Versus VW approx normal, median one third of max.
Source paper
extracted_fromNicholas L. Turner · Jeffrey Wu · Joshua Batson
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Large virtual weights are not inherently misleading but not guaranteed to be helpful or effectivesupportsCaution for practitioners.
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.
- ~27,000 point comparison.
- 15% density.
- Logit-minus-mean-logit loss was most effective for attribution, vs log-loss which was confusing to interpretfinding0.714Attribution loss selection.
- Abstract parity feature.
- Three regimes by effectiveness.
- Justifies the choice of response tokens for persona vector extraction in the pipeline
- Quantitative threshold used for accepting reduced models; linked to Bayes factor of ~20
- Key geometry-to-behavior bridge finding in E3; robust to pooling choice, cosine vs. L2, and frozen external encoder