Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Concept Recovery on SYCOPHANCY
Loading...
0.9827
Mean MCC
Linear Probe
0.408204
0.557352
0.7065
0.855648
Feb 14, 2025
Mean MCC
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean MCC
Linear Probe
Evaluation Protocol=Re...
2025.02
0.9827
PythiaSAE
Evaluation Protocol=Re...
2025.02
0.4931
TopK-SAE
Evaluation Protocol=Re...
2025.02
0.4735
JumpReLU SAE
Evaluation Protocol=Re...
2025.02
0.4511
ReLU-SAE
Evaluation Protocol=Re...
2025.02
0.4347
SSAE
Evaluation Protocol=Re...
2025.02
0.4303
Feedback
Search any
task
Search any
task