framework
active
framework:concept-based-interpretabilityConcept-based interpretability
Second approach: propose concepts and find components corresponding to them.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Classifiers trained to predict concepts from activations.
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.
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- 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
- Cases where subspace interventions change model behaviour through parallel pathways rather than the target feature
- Explaining activations without understanding mechanism.
- Advantage of DiffLogic CA over NCA — learned rules are pure binary logic circuits that can be visualized and analyzed
- An interpretability paradigm that explains computation in the model's own terms, rather than imposing top-down abstractions; VPD aims to realize this.