method
active
method:activation-ratio-analysis

Activation ratio analysis

Measures selectivity of weight components for memorized vs clean data.

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.

  • Component of the contrastive retrieval pipeline analyzing activation statistics.
  • Intervention method that adds a learned direction vector to residual stream activations to steer model behavior
  • Activationsconcept0.791
    Internal representations of the model on which probes operate; the method uses activations to rank datapoints.
  • The conventional approach (e.g., SAEs, transcoders) of decomposing activations into interpretable features.
  • Pearson correlation of feature activations across 40M tokens used to measure feature similarity and universality across models
  • Activation Probingconcept0.749
    Technique of reading out model beliefs from internal activations before the final answer token is generated
  • Internals-based approach to which the logit monitor is complementary.
  • Dividing feature activation spectrum into 11 evenly-spaced intervals and sampling uniformly to evaluate monosemanticity across activation levels