We introduce NNsight and NDIF, technologies that work in tandem to enable scientific study of very large neural networks. NNsight is an open-source system that extends PyTorch to introduce deferred remote execution. NDIF is a scalable inference service that executes NNsight requests, allowing users to share GPU resources and pretrained models. These technologies are enabled by the intervention graph, an architecture developed to decouple experiment design from model runtime. Together, this framework provides transparent and efficient access to the internals of deep neural networks such as very large language models (LLMs) without imposing the cost or complexity of hosting customized models individually. We conduct a quantitative survey of the machine learning literature that reveals a growing gap in the study of the internals of large-scale AI. We demonstrate the design and use of our framework to address this gap by enabling a range of research methods on huge models. Finally, we conduct benchmarks to compare performance with previous approaches.
@inproceedings{nnsight-ndif,
title={NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals},
author={Jaden Fiotto-Kaufman and Alexander R. Loftus and Eric Todd and Jannik Brinkmann and Koyena Pal and Dmitrii Troitskii and Michael Ripa and Adam Belfki and Can Rager and Caden Juang and Aaron Mueller and Samuel Marks and Arnab Sen Sharma and Francesca Lucchetti and Nikhil Prakash and Carla Brodley and Arjun Guha and Jonathan Bell and Byron C. Wallace and David Bau},
year={2025},
booktitle={International Conference on Learning Representations (ICLR)}
}