concept
active
concept:sparse-subframeSparse subframe
Mathematical object defining J-space as union of cones.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Superposition HypothesisextendsCore theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
Concepts (1)
concept
- Gurnee et al.'s privileged set of verbalisable representations behaving as a within-pass global workspace.
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.
- Coding scheme where qualities are represented by few neurons with continuous similarity relations.
- Method from Gurnee et al. 2023 for finding feature directions including individual neuron analysis
- Sparse dictionary learning variant that reads and writes to multiple layers or models, yielding shared features.
- Mechanistic finding by Bricken et al. 2023 about how LLMs store features; cited as operational justification for pattern-repository assumption
- The hypothesis that semantic concepts in neural representations can be captured using sparsity priors
- The extracted set of sparse interpretable features from model embeddings via SAEs
- A goal in mechanistic interpretability to identify sparse computational subgraphs; VPD promotes sparse parameter circuits.
- Interpretability framework used to decompose layer-40 activations into sparse feature sets for studying emotional alignment and persistence