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 0.1B • Updated Mar 10, 2024 • 57 lovish/SAE-tiny-stories-2L-33M-L1-229 0.1B • Updated Mar 10, 2024 • 65 lovish/SAE-tiny-stories-2L-33M-L1-230 0.1B • Updated Mar 10, 2024 • 62 lovish/SAE-tiny-stories-2L-33M-L1-236 0.1B • Updated Mar 10, 2024 • 61
Pythia-70M SAEs lovish/SAE-pythia-70m-L2-11 Updated Mar 10, 2024 • 5 lovish/SAE-pythia-70m-L0-15 Updated Mar 10, 2024 • 9 lovish/SAE-pythia-70m-L3-16 Updated Mar 10, 2024 • 5 lovish/SAE-pythia-70m-L1-19 Updated Mar 10, 2024 • 6
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 0.1B • Updated Mar 10, 2024 • 57 lovish/SAE-tiny-stories-2L-33M-L1-229 0.1B • Updated Mar 10, 2024 • 65 lovish/SAE-tiny-stories-2L-33M-L1-230 0.1B • Updated Mar 10, 2024 • 62 lovish/SAE-tiny-stories-2L-33M-L1-236 0.1B • Updated Mar 10, 2024 • 61
Pythia-70M SAEs lovish/SAE-pythia-70m-L2-11 Updated Mar 10, 2024 • 5 lovish/SAE-pythia-70m-L0-15 Updated Mar 10, 2024 • 9 lovish/SAE-pythia-70m-L3-16 Updated Mar 10, 2024 • 5 lovish/SAE-pythia-70m-L1-19 Updated Mar 10, 2024 • 6