The geometry of hidden representations of large transformer models

Lucrezia Valeriani, Diego Doimo, Francesca Cuturello, Alessandro Laio, Alessio Ansuini, Alberto Cazzaniga. The geometry of hidden representations of large transformer models. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

@inproceedings{ValerianiDCLAC23,
  title = {The geometry of hidden representations of large transformer models},
  author = {Lucrezia Valeriani and Diego Doimo and Francesca Cuturello and Alessandro Laio and Alessio Ansuini and Alberto Cazzaniga},
  year = {2023},
  url = {http://papers.nips.cc/paper_files/paper/2023/hash/a0e66093d7168b40246af1cddc025daa-Abstract-Conference.html},
  researchr = {https://researchr.org/publication/ValerianiDCLAC23},
  cites = {0},
  citedby = {0},
  booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
  editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}