concept
active
concept:disentangled-latent-basisDisentangled Latent Basis
SAE-derived representation space where individual dimensions activate for distinct concepts, enabling cleaner steering
Neighborhood — ranked by edge-count
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.
- Adjacent ML literature on separating independent factors of variation; related to but distinct from the polysemanticity problem studied here
- CIMC's characterization of part of the solution to the Hard Problem: insight into the structural necessities of phenomenal representation
- Related research agenda seeking representations that separate conceptually distinct factors; contrasted with superposition approach
- Reasoning approach using learnable hidden embeddings.
- Statistical regularities stored in pretrained models.
- Hidden or underdeveloped structures existing 'between the lines' of a configuration that can be enhanced and developed through harmony-seeking computation.
- The categorical representation produced by the VAE encoder; used as input to the self-prior and policy networks
- Output of alignment map ϕ applied to DNN hidden states; basis for distributed causal abstraction