lovish/SAE-tiny-stories-2L-33M-L1-228
0.1B • Updated • 2
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-L1-229
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-230
0.1B • Updated • 4 -
lovish/SAE-tiny-stories-2L-33M-L1-236
0.1B • Updated • 3 -
lovish/SAE-tiny-stories-2L-33M-L1-262
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-263
0.1B • Updated • 3 -
lovish/SAE-tiny-stories-2L-33M-L1-264
0.1B • Updated • 3 -
lovish/SAE-tiny-stories-2L-33M-L1-265
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-266
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-267
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-268
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-269
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-273
0.1B • Updated • 3 -
lovish/SAE-tiny-stories-2L-33M-L1-277
0.1B • Updated • 3 -
lovish/SAE-tiny-stories-2L-33M-L1-278
0.1B • Updated • 4 -
lovish/SAE-tiny-stories-2L-33M-L1-289
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-290
0.1B • Updated • 2 -
lovish/SAE-tiny-stories-2L-33M-L1-291
0.1B • Updated • 2