method
active
method:tuned-lens

Tuned lens

Baseline lens that skips ahead to output.

Neighborhood — ranked by edge-count

Methods (3)

method
  • Logit Lens
    extends
    Unsupervised interpretability technique that projects activations through unembedding matrix; provides comparison point for NLA approach.
  • Gurnee et al.'s interpretability method used to identify the J-space workspace.
  • Template lens
    analogous_to
    Multi-token extension via whitened mean-activation templates.

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.