Neuron-level interpretability of looped LMs
Burny
BurnyCoder
AI & ML interests
deep learning, LLMs, interpretability, science, physics
Recent Activity
updated a collection 8 minutes ago
Looped-LM neurons updated a dataset 16 minutes ago
BurnyCoder/ouro-1.4b-neuron-atlas published a dataset 16 minutes ago
BurnyCoder/ouro-1.4b-neuron-atlasOrganizations
models 54
BurnyCoder/grokking-modular-addition-runs
Updated
BurnyCoder/grokking-modular-addition-transformer
Other • Updated
BurnyCoder/ministrike-selfplay-seed333
Reinforcement Learning • Updated • 12
BurnyCoder/ministrike-selfplay-seed222
Reinforcement Learning • Updated • 10
BurnyCoder/ministrike-selfplay-seed111
Reinforcement Learning • Updated • 10
BurnyCoder/ministrike-fixed-seed333
Reinforcement Learning • Updated • 12
BurnyCoder/ministrike-fixed-seed222
Reinforcement Learning • Updated • 12
BurnyCoder/ministrike-fixed-seed111
Reinforcement Learning • Updated • 12
BurnyCoder/ministrike-duel-fixed-v1-diag-ego-r1-seed5201
Reinforcement Learning • Updated • 12 • 1
BurnyCoder/ministrike-duel-fixed-v1-diag-entropy-r1-seed5201
Reinforcement Learning • Updated • 10