method
active
method:logistic-regression-probeLogistic Regression Probe
Standard linear probing technique; compared to mass-mean probing for classification accuracy and causal implication
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Mass-Mean ProbingextendsIntroduced in this paper: an optimization-free probing technique using difference-in-means direction with optional covariance correction
Concepts (1)
concept
- Maximum Margin SeparatorimplementsThe direction logistic regression converges to on linearly separable data; shown to be suboptimal for identifying truth direction
Methods (1)
method
- Logistic regression correctness proberelated_toLogistic regression trained on GSM8k training set to predict answer correctness from projection features along reflection direction
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.
- Ridge regression fit on top-256 PCs of Gemini embeddings to predict model layer-40 activations and compute residuals
- Method used to predict model activations from Gemini embeddings and compute residuals for probe construction
- Linear classifier approach applied to model activations to identify which training datapoints caused undesired behaviors in post-training.
- Interpretability tools that decode information from internal model activations; here, linear probes are used for data attribution.
- Sigmoid fit linking S to success probability.
- Probe method combining causal interventions and structural analysis, supported by pyvene's activation collection
- Fitting a logistic function to success probability as a function of S or shot count to estimate midpoints and widths.
- Simple linear classifiers trained on model activations used as the probing technique within the introduced method.