method
active
method:automated-interpretability-pipeline

Automated interpretability pipeline

Claude-based explanation of features from max-activating examples.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Proposed AI scientists that hypothesize and experiment on features.

Methods (4)

method

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.

  • Method using large language models (Claude) to generate and test explanations of features at scale
  • interpretabilityconcept0.814
    The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
  • Socio-philosophical open question.
  • Detection-based LLM judging of latent descriptions using gpt-4o-mini.
  • Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies
  • Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
  • Programming technique to restructure a fine-grained Linda program for efficiency by replacing live data structures with passive ones and coarser-grain processes.
  • The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper