method
active
method:activation-ratio-analysisActivation ratio analysis
Measures selectivity of weight components for memorized vs clean data.
Neighborhood — ranked by edge-count
Papers (1)
paper
- From Memorization to Reasoning in the Spectrum of Loss Curvatureintroducesmentions
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.
- 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
- 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
- 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