Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spurious Correlation Removal on SAEBench Spurious Correlation Removal Pythia-70M activations
Loading...
2.1
Bias (Professor vs Nurse)
Ensembling (NB)
1.92
3.135
4.35
5.565
May 21, 2025
Bias (Professor vs Nurse)
Bias (Architect vs Journalist)
Bias (Surgeon vs Psychologist)
Bias (Attorney vs Teacher)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Bias (Professor vs Nurse)
Bias (Architect vs Journalist)
Bias (Surgeon vs Psychologist)
Bias (Attorney vs Teacher)
Ensembling (NB)
Ensemble size=8, Appro...
2025.05
2.1
0.4
1.4
0.3
Expanded SAE
2025.05
4.7
0.6
3.7
2.1
Ensembling (Boosting)
Ensemble size=8, Appro...
2025.05
6.6
1.3
4.5
2.9
Feedback
Search any
task
Search any
task