Balanced Subspaces

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Subspace DASmethod0.777
  Extension of DAS that learns a second rotation matrix on top of a fixed first one to decompose representations into sub-representations.
• Behaviorally Binary Subspaceconcept0.771
  A vector subspace that causally impacts outputs only through the sign of its values, enabling harmless magnitude divergence
• Truth Subspaceconcept0.767
  The multi-dimensional activation subspace whose directions causally mediate truthful behavior in LLMs
• Emotion Subspaceconcept0.753
  The subspace of activation space spanned by the 171 orthogonalized emotion probe vectors, used to measure SAE feature emotional alignment
• Subspace Decomposition of Representationsconcept0.753
  Investigation of whether a distributed representation can be further decomposed into sub-representations encoding component identities.
• Subspace Interventionconcept0.748
  Intervention targeting specific dimensional subsets of activation vectors rather than full representations
• Two-dimensional truth subspaceframework0.745
  Burger et al. (2024) framework proposing that truth is linearly decoded along a 2D subspace capturing both polarity-dependent and polarity-invariant directions.
• Intervention on a balanced subspace dimension while holding others fixed crosses the decision boundary using a non-native mechanismfinding0.736
  Additional synthetic example of pernicious divergence from balanced subspaces