concept
active
concept:interpretabilityinterpretability
The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Interpretability Illusionrelated_toCases where subspace interventions change model behaviour through parallel pathways rather than the target feature
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.
- Socio-philosophical open question.
- Method using large language models (Claude) to generate and test explanations of features at scale
- Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies
- Second approach: propose concepts and find components corresponding to them.
- Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
- CIMC's methodology for evaluating whether a built system is conscious: combining multiple forms of evidence including predicted functional organization and developmental trajectories
- Explaining activations without understanding mechanism.
- Ian Goodfellow quote used to illustrate the pre-paradigmatic state of interpretability research