Visualizing grokking modular addition - a BurnyCoder Collection

BurnyCoder 's Collections

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 about 16 hours ago

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

BurnyCoder/grokking-modular-addition-runs

Updated about 10 hours ago

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

Updated about 10 hours ago • 10

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

Other • Updated Mar 1

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)