jln.shk_64x4: JSAE (resid_mid -> resid_out) 7.5k steps
j.mlp_layer.shk_64x4: JSAE (mlp_in -> mlp_out) 7.5k steps
David Quarel
davidquarel
·
AI & ML interests
None yet
Recent Activity
updated a model about 2 hours ago
timaeus/jaxgmg2_alpha1_patt updated a model about 2 hours ago
timaeus/jaxgmg2_3phase_optim_state_alpha1 updated a model about 3 hours ago
timaeus/al_1.0_g_0.98_x100Organizations
models 153
davidquarel/fineweb_10b_gpt2
Updated
davidquarel/fineweb_gpt2
Updated
davidquarel/sc.mlpblock.gpt2.k32.x32
0.1B • Updated
davidquarel/jln.shk_64x4-20k
Updated
davidquarel/j.mlp_layer.shk_64x4-20k
Updated
davidquarel/j.mlp_layer.shk_64x4
Updated
davidquarel/jln.shk_64x4
Updated
davidquarel/jln.mlpblock.gpt2-sparse-1.0e-20
0.1B • Updated
davidquarel/jln.mlpblock.gpt2-sparse-1.0e-10
0.1B • Updated
davidquarel/jln.mlpblock.gpt2-sparse-1.0e-15
0.1B • Updated