finding
active
finding:under-gaussian-noise-the-predictive-similarity-map-coarsens-into-larger-blocks-and-variance-explained-decays-slower-than-saes-which-drop-to-0Under Gaussian noise the predictive similarity map coarsens into larger blocks and variance explained decays slower than SAEs, which drop to ~0.
Fig. 7d,e.
Source paper
extracted_from(2025) · Lubana, Ekdeep Singh · Rager, Can · Hindupur, Sai Sumedh R. · Costa, Valerie +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- Motivates noise analysis.
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.
- Fig. 7c over 50 GPT-5 stories.
- Robustness influences superposition, predicting lower SAE loss in more robust models.hypothesis0.794Popperian credit for surprising prediction.
- Discrete case.
- Fig. 8b,c.
- Sampling noise decreases in proportion to 1/√S, giving a linear relation between log TVD and log S.hypothesis0.790Derived from multinomial sampling.
- Robustness check ruling out that any perturbation would decrease type hint rate due to brittleness.
- Appendix B.
- Main result 1.