concept
active
concept:functional-faithfulnessFunctional Faithfulness
Empirical effect where intervening on one feature induces coherent shifts across multiple linguistic dimensions aligned with the target attribute.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (2)
concept
- faithfulnessrelated_toThe condition that commitments are fulfilled.
- Bidirectional Steeringassociated_withAbility to steer model behavior in two opposite semantic directions on a trait.
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.
- Definition of the newly named empirical effect.
- Empirical effect observed in feature intervention experiments.
- Property of explanations that accurately reflect the actual causal mechanisms of the model being explained.
- The deep fit between a building's form and its functional requirements, achieved only through differentiation.
- Idea that decomposed components must causally reflect the model's computation; enforced by adversarial ablation in VPD.
- Epistemological position that what any phenomenon is is its causal/operational role; rejects hidden essence; foundational to CIMC's stance
- Similarity measured with respect to network behavior/function rather than statistical correlation of activations.
- One of the three major competing approaches to parallel programming mentioned in the paper; used for comparison with Linda.