if you haven't seen it, this one is great too: aclanthology.org/2021.emnlp-m...

All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality

William Timkey, Marten van Schijndel. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

Wow, this is building up to a nice corpus. Though id definitely tape on a warning label on this corpus, like “epistemological nihilism, we know nothing!” 😂