Sparse Rewiring enables neuron-level interpretation of what fine-tuning changes
maxsloef · x · 2026-11-11
Sparse Rewiring offers a new angle on neuron and training interpretability: with only 89 changed neurons, each can be interpreted in detail, training data can locate relevant neurons, and training's effects can be understood mechanistically.
More from Research
- Brynjolfsson's GDP-B paper quantifies the welfare value of free goods like Facebook, published in AEJ — soumitrashukla9 · 2026-11-12
- Cells rejuvenated to under 20: the case for Longevity Escape Velocity — Dr_Singularity · 2026-11-12
- Over 50 ICLR 2027 papers are named PRISM, and that says something about research naming — deliprao · 2026-11-12
- 37% on ARC-AGI-2 Kaggle With a 100M Looped Transformer Trained From Scratch, No LLM — rbhar90 · 2026-11-12
- Loom lens: sampling the MTP head like a language model to get tree-shaped activation readouts — voooooogel · 2026-11-12
- Interpreting all 1.1M MLP neurons in Qwen 27B with chain lens for just $5 — voooooogel · 2026-11-12