Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sparse Autoencoder Evaluation on SAEBench Pythia-160M (test)
Loading...
0.502
RAVEL Score
Ensembling (Boosting)
0.496696
0.498073
0.49945
0.500827
May 21, 2025
RAVEL Score
CE Loss Score
TPP
Updated 1mo ago
Evaluation Results
Method
Method
Links
RAVEL Score
CE Loss Score
TPP
Ensembling (Boosting)
Language Model=Pythia-...
2025.05
0.502
1
0.2701
Ensembling (NB)
Language Model=Pythia-...
2025.05
0.4977
0.9829
0.0163
Expanded SAE
Language Model=Pythia-...
2025.05
0.497
0.9783
0.2886
Base SAE
Language Model=Pythia-...
2025.05
0.4969
0.9771
0.2635
Feedback
Search any
task
Search any
task