concept
active
concept:feature-absorptionFeature Absorption
Phenomenon where sparsity yields gerrymandered latents for hierarchical concepts.
Neighborhood — ranked by edge-count
Papers (3)
paper
Methods (1)
method
- Adapted absorption metric detecting partial and shared absorption across layers.
Concepts (2)
concept
- Feature splitting and absorptionrelated_toProblems suggesting sparsity breaks down as interpretability proxy.
- Feature splittingassociated_withPhenomenon where a feature in a small SAE splits into multiple finer features in a larger SAE.
Questions (1)
question
- Open question about feature cluster.
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.
- Synthesizing inputs maximizing component activation.
- Interpretable concept representations hypothesized as basic units of computation.
- Functionally significant directions in the residual stream that organize activations in mechanistic interpretability
- When non-orthogonal features cause logistic regression to identify a suboptimal probe direction
- Features with similar decoder magnitude across both models.
- 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.
- Frequency-weighted spectral value πkλkj determining which features are retained.