Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Out-of-Distribution Detection on 20NG (ID) vs SST-2 (OOD)
Loading...
0.9988
AUROC
Gemma2-2b LR baseline
0.977376
0.982938
0.9885
0.994062
May 12, 2026
AUROC
AUPR (OOD)
FPR@95
Updated 21d ago
Evaluation Results
Method
Method
Links
AUROC
AUPR (OOD)
FPR@95
Gemma2-2b LR baseline
Backbone=Gemma2-2b, Ba...
2026.05
0.9988
0.9871
0.27
Gemma2-9b LR baseline
Backbone=Gemma2-9b, Ba...
2026.05
0.998
0.9994
0.4
Gemma2-9b + 16k SAE + Markov
Backbone=Gemma2-9b, SA...
2026.05
0.9866
0.8713
6.65
Gemma2-2b + 16k SAE + Markov
Backbone=Gemma2-2b, SA...
2026.05
0.9782
0.7683
11.01
Feedback
Search any
task
Search any
task