Out-of-Distribution Detection on 20NG (ID) vs SST-2 (OOD)
0.9988AUROCGemma2-2b LR baseline
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Gemma2-2b LR baselineBackbone=Gemma2-2b, Backend=Logistic Regression, Training Protocol=ID-only training2026.05 | 0.9988 | 0.9871 | 0.27 | |
| Gemma2-9b LR baselineBackbone=Gemma2-9b, Backend=Logistic Regression, Training Protocol=ID-only training2026.05 | 0.998 | 0.9994 | 0.4 | |
| Gemma2-9b + 16k SAE + MarkovBackbone=Gemma2-9b, SAE Size=16k, Backend=Markov, Training Protocol=ID-only training2026.05 | 0.9866 | 0.8713 | 6.65 | |
| Gemma2-2b + 16k SAE + MarkovBackbone=Gemma2-2b, SAE Size=16k, Backend=Markov, Training Protocol=ID-only training2026.05 | 0.9782 | 0.7683 | 11.01 |