InversionView: A General-Purpose Method for Reading Information from Neural Activations (bibtex)
by Xinting Huang, Madhur Panwar, Navin Goyal, Michael Hahn
Reference:
InversionView: A General-Purpose Method for Reading Information from Neural ActivationsXinting Huang, Madhur Panwar, Navin Goyal, Michael HahnThe Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024), 2024.
Bibtex Entry:
@inproceedings{
huang2024inversionview,
title={InversionView: A General-Purpose Method for Reading Information from Neural Activations},
author={Xinting Huang and Madhur Panwar and Navin Goyal and Michael Hahn},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)},
note={Second Prize at the ICML 2024 Workshop on Mechanistic Interpretability},
year={2024},
url={https://arxiv.org/abs/2405.17653}
}
Powered by bibtexbrowser