Neuron-level interpretability of looped LMs
Burny
BurnyCoder
AI & ML interests
deep learning, LLMs, interpretability, science, physics
Recent Activity
liked a model about 5 hours ago
ByteDance/Ouro-1.4B-Thinking liked a model about 5 hours ago
ByteDance/Ouro-1.4B updated a collection about 6 hours ago
Looped-LM neuronsOrganizations
Fixed-spawn duel self-play: all confirmation and exploratory pairs, plus deferred 5v5 archives. Experimental; moving-script acceptance failed.
-
BurnyCoder/ministrike-selfplay-cpu
Reinforcement Learning • Updated • 12 -
BurnyCoder/ministrike-selfplay-cuda
Reinforcement Learning • Updated • 17 -
BurnyCoder/ministrike-duel-fixed-v1-seed5101
Reinforcement Learning • Updated • 11 -
BurnyCoder/ministrike-duel-fixed-v1-seed5102
Reinforcement Learning • Updated • 13
Retrained runs, website data and original checkpoints of the transformer that groks modular addition.
MaskablePPO and behaviour-cloned 4D snake networks (2^4, 3^4, 4^4 boards) with configs, evaluation files and cards; negative results included.
-
BurnyCoder/4d-snake-exp02-ppo-2x4
Reinforcement Learning • Updated • 20 -
BurnyCoder/4d-snake-exp02b-ppo-2x4-backplay
Reinforcement Learning • Updated • 9 -
BurnyCoder/4d-snake-exp02c-ppo-2x4-long
Reinforcement Learning • Updated • 11 -
BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict
Reinforcement Learning • Updated • 13
Public evidence and retained failed or inconclusive LoRA checkpoints from the Atemokoloporos synthetic-fact study.
-
BurnyCoder/atemokoloporos-qwen3.5-0.8b-study-evidence
Updated • 62 -
BurnyCoder/qwen3.5-0.8b-atemokoloporos-positive-primary
Text Generation • Updated • 11 -
BurnyCoder/qwen3.5-0.8b-atemokoloporos-positive-conservative
Text Generation • Updated • 7 -
BurnyCoder/qwen3.5-0.8b-atemokoloporos-positive-expanded
Text Generation • Updated • 14
Pre-registered interchange interventions (concept swaps) testing Circuits neuron explanations in InceptionV1: data and results.
Single-seed pilot comparing frozen LLM-judge and probe monitors. Checkpoints and evidence; no established safety guarantee.
All reported MNIST/CIFAR-10 models, paired seeds, controls, and reproducible evidence.
Completed reviewed LoRA experiment runs from the Qwen3.8-27B Atemokoloporos synthetic-fact study.
Exact trained reproductions of Goodfire’s README quickstart and three starter notebooks using DINOv3 ViT-B/16 rabbit patch activations.
Neuron-level interpretability of looped LMs
Pre-registered interchange interventions (concept swaps) testing Circuits neuron explanations in InceptionV1: data and results.
Fixed-spawn duel self-play: all confirmation and exploratory pairs, plus deferred 5v5 archives. Experimental; moving-script acceptance failed.
-
BurnyCoder/ministrike-selfplay-cpu
Reinforcement Learning • Updated • 12 -
BurnyCoder/ministrike-selfplay-cuda
Reinforcement Learning • Updated • 17 -
BurnyCoder/ministrike-duel-fixed-v1-seed5101
Reinforcement Learning • Updated • 11 -
BurnyCoder/ministrike-duel-fixed-v1-seed5102
Reinforcement Learning • Updated • 13
Single-seed pilot comparing frozen LLM-judge and probe monitors. Checkpoints and evidence; no established safety guarantee.
Retrained runs, website data and original checkpoints of the transformer that groks modular addition.
All reported MNIST/CIFAR-10 models, paired seeds, controls, and reproducible evidence.
MaskablePPO and behaviour-cloned 4D snake networks (2^4, 3^4, 4^4 boards) with configs, evaluation files and cards; negative results included.
-
BurnyCoder/4d-snake-exp02-ppo-2x4
Reinforcement Learning • Updated • 20 -
BurnyCoder/4d-snake-exp02b-ppo-2x4-backplay
Reinforcement Learning • Updated • 9 -
BurnyCoder/4d-snake-exp02c-ppo-2x4-long
Reinforcement Learning • Updated • 11 -
BurnyCoder/4d-snake-exp02d-ppo-2x4-backplay-strict
Reinforcement Learning • Updated • 13
Completed reviewed LoRA experiment runs from the Qwen3.8-27B Atemokoloporos synthetic-fact study.
Public evidence and retained failed or inconclusive LoRA checkpoints from the Atemokoloporos synthetic-fact study.
-
BurnyCoder/atemokoloporos-qwen3.5-0.8b-study-evidence
Updated • 62 -
BurnyCoder/qwen3.5-0.8b-atemokoloporos-positive-primary
Text Generation • Updated • 11 -
BurnyCoder/qwen3.5-0.8b-atemokoloporos-positive-conservative
Text Generation • Updated • 7 -
BurnyCoder/qwen3.5-0.8b-atemokoloporos-positive-expanded
Text Generation • Updated • 14
Exact trained reproductions of Goodfire’s README quickstart and three starter notebooks using DINOv3 ViT-B/16 rabbit patch activations.