claim
active
claim:if-superposition-is-a-primary-cause-there-is-a-fundamental-unavoidable-trade-off-between-robustness-and-model-capacity-and-interpretability-and-robustness-are-alignedIf superposition is a primary cause, there is a fundamental unavoidable trade-off between robustness and model capacity, and interpretability and robustness are aligned.
Discussion implication.
Source paper
extracted_from(2025) · Gorton, Liv · Lewis, Owen
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central thesis.
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.
- Superposition may be a major contributing factor, or even the primary cause, of adversarial examples.hypothesis0.818Hypothesis under test.
- Supported by Table 1.
- Robustness influences superposition, predicting lower SAE loss in more robust models.hypothesis0.811Popperian credit for surprising prediction.
- Posed on SAE results.
- Confound addressed.
- superposition is deeply linked to the ability to identify and enumerate over all features in a modelquote0.795Safety rationale.
- Open question.
- Interpretation of the cars-in-superposition circuit finding as an intentional representational strategy