NNterp 2.0 launches: run the same NNsight interpretability experiment across ~all LLMs
gsarti_ · x · 2026-11-19
NNterp 2.0 is out: a unified interface for NNsight that abstracts away the quirks of hundreds of transformer models, so the same interpretability experiment code works across essentially all LLMs. A practical win for mechanistic-interpretability researchers who previously had to adapt experiments per model.
More from Research
- CONGA compiler exploits Gaussian block geometry for Bayesian inference, 12.5x ESS/s gain for NUTS — Víctor Gallego · 2026-11-19
- GPT 6.2 Astra shows surprisingly strong zero-shot crystal generation, a year after the task looked hopeless — xennygrimmato_ · 2026-11-19
- Universal Data-Efficient Pretraining Claims 56x Gains on Molecules, 24x on DNA and Crystals — madhavsinghal_ · 2026-11-19
- Fine-tuned World Action Model Dream-1 Jumps 159%, Beats Frontier LLMs on Robot Tasks — paigeinsf · 2026-11-19
- AI makes 'living papers' nearly free to build, but their durability is doubtful — _akpiper · 2026-11-19
- HiT image generator hits 1.48 FID learning hierarchy from pixels, fast reproduced — niloofar_mire · 2026-11-19