concept
active
concept:class-centroid-difference-initializationClass-Centroid Difference Initialization
Method of initializing control vectors as difference between mean SAE codes for positive and negative samples
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.
- Method for extracting linear directions by subtracting mean activations of contrastive groups; used to define the Assistant Axis
- Formal consequence of Belrose et al. (2023) Theorem G.1 connecting mass-mean probing to optimal linear concept erasure
- Gradient that tells a cell its correct position; stress arises from deviation from this gradient.
- Mechanism for encoding sequence order in transformers; paper argues these should reflect learned structural representations rather than fixed sines/cosines.
- Central design question of denotational methodology; asks what semantic meaning should precede implementation choice.
- Combining α1 with τ (type) and β1 with σ (supertype) to model class-based OO with inheritance in the associative model.