concept
active
concept:privileged-basisPrivileged Basis
A property of activations where neural network features align with basis dimensions due to sparse activation functions; absent in the residual stream but present in tokens, attention patterns, and MLP activations
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Polysemanticityassociated_withNeurons that respond to multiple unrelated concepts, limiting interpretability.
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.
- Hypothesis that neurons form privileged bases to encode information; consistent with constructive abstraction
- Models predict their own hypothetical behavior better than other models can, demonstrating a form of privileged self-access per Binder et al. 2024
- Minds not exclusively neural; basal cognition identifies intelligences in single cells, plants, tissues, swarms; brains pre-date neurons evolutionarily.
- A set of feature directions that is larger than the dimensionality of the space, enabling superposition
- Attribute: providing a foundation function, a text that acts as base or corroboration.
- The emotional substance originating from one's own humanity that must be put into making for life to appear.
- The sense in which a person is justified in holding a belief, tied to phenomenal consciousness.