latent-lab/smaller-than-truth-qwen2.5-1.5b

lmprobe: Linear Probe on Qwen2.5-1.5B

Truth probe for 'X is smaller than Y' statements. Perfect accuracy (100%) — structural/relational knowledge is robust at 1.5B scale.

Classes

• 0: false_statement
• 1: true_statement

Usage

from lmprobe import LinearProbe

probe = LinearProbe.from_hub("latent-lab/smaller-than-truth-qwen2.5-1.5b", trust_classifier=True)
predictions = probe.predict(["your text here"])

Probe Details

• Base model: Qwen/Qwen2.5-1.5B
• Model revision: 8faed761d45a263340a0528343f099c05c9a4323
• Layers: all (0–27, 28 layers)
• Pooling: last_token
• Classifier: logistic_regression
• Task: classification
• Random state: 42

Evaluation

Metric	Value
accuracy	1.0000
auroc	1.0000
f1	1.0000
precision	1.0000
recall	1.0000

Training Data

• Positive examples: 792

• Negative examples: 792

• Positive hash: sha256:55f43cad0c06e9599839603d3c513543de4ca71eed2b22cccb16542930f6e2b8

• Negative hash: sha256:d9f02b07f2025712a6dd175310f7af58ee761c73b40792e10cf06335953628c0

• Evaluation samples: 396

• Evaluation hash: sha256:546af552622d90b1e54d88d3111f68aa201178f0458267da51ecbe393443e821

Reproducibility

• lmprobe version: 0.5.8
• Python: 3.12.3
• PyTorch: 2.10.0+cu128
• scikit-learn: 1.8.0
• transformers: 5.3.0