finding
active
finding:inverse-scr-scaling-persists-across-intervention-sizes-for-non-hierarchical-architecturesInverse SCR scaling persists across intervention sizes for non-hierarchical architectures
Rules out fraction-modified explanation.
Source paper
extracted_from(2025) · Adam Karvonen · Can Rager · Johnny Lin · Curt Tigges +11
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (2)
hypothesis
- Explains inverse scaling.
- Alternative hypothesis tested and rejected.
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.
- Margin of advantage.
- Inverse scaling on SCR.
- Claim about broader applicability of the scaling argument
- Scaling causal interventions on codes will move from qualitative alignment to mechanistic claims.hypothesis0.757Future work.
- Central unresolved question about the mechanism behind ESR's apparent size-dependence
- Cited hypothesis from Lin et al. 2022 suggesting larger models become more capable of deception
- Author's emphasis on the interpretive nature of scaling.
- Implication of PRH: larger models should amplify bias less and hallucinate less if they better model reality