method
active
method:linear-and-attention-probesLinear and attention probes
Classifiers used for token filtering and reward shaping.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (2)
method
- Linear Proberelated_toSimple linear classifiers trained on model activations used as the probing technique within the introduced method.
- Linear Probe for Evaluation Awarenessrelated_toNguyen et al. trained linear probes on activations to distinguish evaluation from deployment scenarios.
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.
- Used to characterize counting representations.
- Used to evaluate representation quality across VTAB tasks
- Method for fitting a linear classifier on collected activations to predict task-relevant features
- Interpretation of Fig. 9.
- Method to select d_steer top-activated SAE features for constructing control vectors
- One of four emotive concept probes trained; contrastive pair distracted/focused with best layer 10 in LLaMA-3.2-3B
- Uses normalized probe weights as steering vector.