method
active
method:pca-and-multinomial-logistic-regression-probesPCA and multinomial logistic regression probes
Used to test linear separability of group position.
Neighborhood — ranked by edge-count
Papers (1)
paper
Hypotheses (1)
hypothesis
- Positional signal is diffuse because the model encodes group positions in a poorly linearly separable way for middle groupsassociated_withTested via probes.
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.
- Standard linear probing technique; compared to mass-mean probing for classification accuracy and causal implication
- Reveals low-dimensional counting manifolds.
- Statistical method used to analyze neural activity data.
- Logistic regression trained on GSM8k training set to predict answer correctness from projection features along reflection direction
- 15-way classifier of emotion over five dialogue conditions.
- Limitations of PCA.
- Used to characterize counting representations.
- Intrinsic noise in representation.