Features (mechanistic interpretability)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Circuit (mechanistic interpretability)concept0.808
  An inference path across features that constitutes a computational subgraph in a trained model
• interpretabilityconcept0.805
  The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
• Interpretability features converge across different model architectures, revealing structural similarities.claim0.774
• Feature engineeringconcept0.771
  Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
• Automated Interpretabilityframework0.768
  Method using large language models (Claude) to generate and test explanations of features at scale
• Circuit Interpretabilityconcept0.768
  Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
• How can mechanistic interpretability methods automatically identify attention computations that span multiple attention heads?question0.767
  Long-standing bottleneck in mechanistic interpretability that VPD addresses by working natively on attention weight matrices.
• Interpretability Illusionconcept0.764
  Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature