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.

Original post →

More from Research

Research channel →