method
active
method:concept-vector-computationconcept vector computation
Procedure extracting concept vectors as difference of mean activations between concept-exemplifying and baseline/negative sentences
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 edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Computed directional vector in activation space representing a specific concept, used for injection experiments
- Probabilistic framework formalizing concept-specific subspaces for targeted steering in generative models.
- The spatial/geometric organization of conceptual structure within neural network representations; central to the paper's thesis.
- Method for obtaining concept vectors by subtracting activations from two contrasting prompts.
- Central entity of Jackson's framework: a structure invented to give coherent account of immediate consequences of actions; the building block of software design
- How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.