concept
active
concept:behaviorally-binary-subspaceBehaviorally Binary Subspace
A vector subspace that causally impacts outputs only through the sign of its values, enabling harmless magnitude divergence
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Behavioral Null Spaceassociated_withThe span of vector directions that do not change network behavior; a key concept distinguishing MAS from model stitching.
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.
- A geometric space of all output token probability distributions, equipped with Hellinger distance, used to visualize model behavior.
- The multi-dimensional activation subspace whose directions causally mediate truthful behavior in LLMs
- The traditional space of movement in the physical world where animals exhibit problem-solving behavior.
- The subspace of activation space spanned by the 171 orthogonalized emotion probe vectors, used to measure SAE feature emotional alignment
- Extension of DAS that learns a second rotation matrix on top of a fixed first one to decompose representations into sub-representations.
- Contiguous subspace of the aligned latent vector encoding behaviorally relevant information for a specific causal variable.
- Subspaces whose contributions to a layer's output are canceled by opposing weight values, making them non-causally active under natural inputs
- Burger et al. (2024) framework proposing that truth is linearly decoded along a 2D subspace capturing both polarity-dependent and polarity-invariant directions.