framework
active
framework:independent-subspace-analysis

Independent subspace analysis

Learns subspaces with phase invariance; precursor.

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

  • Intervention targeting specific dimensional subsets of activation vectors rather than full representations
  • Subspace DASmethod0.747
    Extension of DAS that learns a second rotation matrix on top of a fixed first one to decompose representations into sub-representations.
  • Truth Subspaceconcept0.742
    The multi-dimensional activation subspace whose directions causally mediate truthful behavior in LLMs
  • Emotion Subspaceconcept0.733
    The subspace of activation space spanned by the 171 orthogonalized emotion probe vectors, used to measure SAE feature emotional alignment
  • Balanced Subspacesconcept0.731
    Subspaces whose contributions to a layer's output are canceled by opposing weight values, making them non-causally active under natural inputs
  • CIMC's proposed evaluation methodology: examining what systems build within themselves and inferring to best explanation
  • Subspace captureconcept0.722
    A small fixed atom group spans the manifold subspace and the encoder consistently selects it.
  • Linear-model solution that trades off with superposition.