method
active
method:contrastive-concept-vector-extraction

Contrastive concept vector extraction

Method for obtaining concept vectors by subtracting activations from two contrasting prompts.

Neighborhood — ranked by edge-count

Methods (1)

method
  • Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.

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.

  • Method using activations from the prompt 'Tell me about {word}' minus mean over other random words to obtain concept vectors.
  • concept vectorconcept0.819
    Computed directional vector in activation space representing a specific concept, used for injection experiments
  • Procedure extracting concept vectors as difference of mean activations between concept-exemplifying and baseline/negative sentences
  • Method comparing brain activity in conscious vs. unconscious conditions.
  • Method for computing steering vectors as mean activation differences between reflection levels at a given layer.
  • Pipeline for extracting mean post-MLP residual stream activations from model responses under persona-specific system prompts to produce role vectors
  • A pipeline employing controlled semantic oppositions to distill monosemantic functional features from sparse activation spaces.
  • How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.