concept
active
concept:sparse-coding-hypothesisSparse Coding Hypothesis
The hypothesis that semantic concepts in neural representations can be captured using sparsity priors
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Candidate approach to solving superposition.
- Coding scheme where qualities are represented by few neurons with continuous similarity relations.
- Mechanism by which superposition works: small neural networks exploit sparsity to approximately simulate much larger sparse networks
- Sparse dictionary learning variant that reads and writes to multiple layers or models, yielding shared features.
- Method from Gurnee et al. 2023 for finding feature directions including individual neuron analysis
- Mathematical object defining J-space as union of cones.
- Deep networks are biased toward finding simple fits to data, and this bias increases with model size, driving convergence
- Extension of SAEs that jointly learns latents across representations from different models; proposed as alternative for extended fine-tuning