Visualizing grokking modular addition - a BurnyCoder Collection

BurnyCoder 's Collections

Looped-LM neurons

Counterfactual concept swaps in CNNs

MiniStrike staged shooter self-play

Qwen3-0.6B GRAFT with LLM-as-a-Judge and Probe Monitors

Visualizing grokking modular addition

Oscillatory flow matching — local exploratory study

4D Snake RL: all evaluated networks

Atemokoloporos Qwen3.8-27B LoRA runs

Atemokoloporos Qwen3.5-0.8B retained checkpoints

Block-Sparse Featurizers on DINOv3 Rabbits

Visualizing grokking modular addition

updated 5 days ago

Retrained runs, website data and original checkpoints of the transformer that groks modular addition.

BurnyCoder/grokking-modular-addition-runs

Updated 1 day ago

Note Our 22 retrained runs (seeds and controls)
BurnyCoder/grokking-modular-addition-site-data

Updated 1 day ago • 78

Note Arrays and float16 weights used by the website
BurnyCoder/grokking-modular-addition-transformer

Other • Updated 1 day ago

Note Earlier TransformerLens replication (seed 999)
callummcdougall/grokking_full_run_data

Updated Jan 14, 2024 • 2

Note The paper's own mainline run (original uploader)