concept
active
concept:feature-importanceFeature importance
Scalar weight on loss for each feature.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
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.
- Interpretable concept representations hypothesized as basic units of computation.
- Prior state-of-the-art baseline using the abliterated model as proposal distribution.
- Features that activate on content related to potential harms (deception, bias, dangerous information).
- Weighted Spearman correlation that corrects for sampling bias in automated interpretability evaluation
- A measure of whether a subcomponent is necessary to reproduce model behavior on a specific prompt, predicted by the causal importance network.
- Extra feature representing unexplained error to make isomorphism exact.
- Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
- Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.