claim
active
claim:linear-probe-based-filtering-acts-like-a-generic-style-probe-causing-off-target-changesLinear-probe-based filtering acts like a generic style probe, causing off-target changes
Interpretation of Fig. 9.
Source paper
extracted_from(2026) · Leon Bergen · Usha Bhalla · Sidharth Baskaran · Max Loeffler +13
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
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.
- Key interpretive question the framework helps address through convergent validation logic
- Key interpretive claim from Case Study II distinguishing probe accuracy from causal relevance
- Nguyen et al. trained linear probes on activations to distinguish evaluation from deployment scenarios.
- Classifiers used for token filtering and reward shaping.
- Self-repair effect.
- Key methodological claim: MM probes are both competitive in accuracy and superior in causal influence
- Used to evaluate representation quality across VTAB tasks
- Used to characterize counting representations.