angerami/pythia-70m-deduped_weight_evolution
Viewer • Updated • 22.2k • 5
Transformer Weight Evolution Study
Attention weight distributions across transformer architectures.
-
-
angerami/pythia-160m-deduped_weight_evolution
Viewer • Updated • 66.5k • 4 -
angerami/pythia-410m-deduped_weight_evolution
Viewer • Updated • 177k • 5 -
angerami/pythia-1b-deduped_weight_evolution
Viewer • Updated • 59.1k • 5 -
angerami/pythia-1.4b-deduped_weight_evolution
Viewer • Updated • 177k • 9 -
angerami/pythia-2.8b-deduped_weight_evolution
Viewer • Updated • 473k • 4 -
angerami/pythia-6.9b-deduped_weight_evolution
Viewer • Updated • 473k • 6 -
angerami/pythia-12b-deduped_weight_evolution
Viewer • Updated • 665k • 5 -
angerami/transformer_weights_cross_model
Viewer • Updated • 27.2k • 12