Orthonormal Basis Vectors

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

• Random vector baselinemethod0.740
  Baseline method sampling a random vector as feature direction for comparison with learned methods
• Sense Vectorsconcept0.724
  Vectors acquired during pretraining in Backpack LMs that have a multiplication effect on model generation
• Change-of-Basis for Neural Representationsconcept0.723
  Key insight that rotating a neural representation to a non-standard basis can reveal distributed causal structure invisible in standard neuron-aligned basis.
• Persona Vectors (Chen et al.)framework0.712
  Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
• Individual cone basis vectors may correspond to interpretable semantic facets of truth such as temporal facts, geographic facts, or commonsensehypothesis0.708
  Future direction hypothesis for giving semantic meaning to individual axes
• steering vectorsconcept0.705
  A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
• Residual Activation Vectorsconcept0.703
  Layer-40 activations with the component explained by compressed Gemini embeddings subtracted, isolating information not driven by surface text content
• What semantic labels correspond to the individual basis vectors of the truth cone?question0.701
  Central open question for future work on interpretability of cone axes