TinyStories SAE Regularization Comparison Comparison of different regularization methods for training SAE models on the layer 1 MLP of TinyStories 2L 33M. lovish/SAE-tiny-stories-2L-33M-L1-228 Updated Mar 10, 2024 • 8 lovish/SAE-tiny-stories-2L-33M-L1-229 Updated Mar 10, 2024 • 9 lovish/SAE-tiny-stories-2L-33M-L1-230 Updated Mar 10, 2024 • 9 lovish/SAE-tiny-stories-2L-33M-L1-236 Updated Mar 10, 2024 • 9
Pythia-70M SAEs lovish/SAE-pythia-70m-L2-11 Updated Mar 10, 2024 • 8 lovish/SAE-pythia-70m-L0-15 Updated Mar 10, 2024 • 10 lovish/SAE-pythia-70m-L3-16 Updated Mar 10, 2024 • 8 lovish/SAE-pythia-70m-L1-19 Updated Mar 10, 2024 • 9
TinyStories SAE Regularization Comparison Comparison of different regularization methods for training SAE models on the layer 1 MLP of TinyStories 2L 33M. lovish/SAE-tiny-stories-2L-33M-L1-228 Updated Mar 10, 2024 • 8 lovish/SAE-tiny-stories-2L-33M-L1-229 Updated Mar 10, 2024 • 9 lovish/SAE-tiny-stories-2L-33M-L1-230 Updated Mar 10, 2024 • 9 lovish/SAE-tiny-stories-2L-33M-L1-236 Updated Mar 10, 2024 • 9
Pythia-70M SAEs lovish/SAE-pythia-70m-L2-11 Updated Mar 10, 2024 • 8 lovish/SAE-pythia-70m-L0-15 Updated Mar 10, 2024 • 10 lovish/SAE-pythia-70m-L3-16 Updated Mar 10, 2024 • 8 lovish/SAE-pythia-70m-L1-19 Updated Mar 10, 2024 • 9