concept
active
concept:interpretability-dark-matter

Interpretability dark matter

Structure SAEs miss.

Neighborhood — ranked by edge-count

Frameworks (1)

framework
  • Feature Manifolds
    associated_with
    Hypothesized extension of superposition where features may be higher-dimensional manifolds rather than 1D directions

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.

  • interpretabilityconcept0.817
    The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
  • Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies
  • Socio-philosophical open question.
  • An interpretability paradigm that explains computation in the model's own terms, rather than imposing top-down abstractions; VPD aims to realize this.
  • Detection-based LLM judging of latent descriptions using gpt-4o-mini.
  • Method using large language models (Claude) to generate and test explanations of features at scale
  • The field aimed at understanding what neural networks have learned; characterized as pre-paradigmatic in this paper
  • Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature