method
active
method:targeted-probe-perturbation-tppTargeted Probe Perturbation (TPP)
Novel multiclass generalization of SCR.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- SAEBenchusesEvaluation suite of eight metrics across four capabilities.
Concepts (1)
concept
- Independent concepts are encoded by separate latents.
Methods (2)
method
- Novel metric extending SHIFT via zero ablation.
- Stronger test of concept isolation than steering.
Datasets (2)
dataset
- Amazon ReviewsusesUsed for probing, SCR, TPP.
- Bias in BiosusesUsed for sparse probing, SCR, TPP.
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.
- Interpretation of resampling.
- Linear classifier approach applied to model activations to identify which training datapoints caused undesired behaviors in post-training.
- Causal transformer probe predicting whether a token is in the same Entity as its predecessor.
- Standard interpretability technique used to read feature beliefs.
- Probing approach avoiding supervision to sidestep complexity-accuracy tradeoff
- Earlier interpretability method applying classifiers to DNN hidden representations; shares complexity-accuracy dilemma with causal abstraction
- The ability of probes trained on one dataset to transfer accurately to topically and structurally different datasets
- Internals-based approach to which the logit monitor is complementary.