Understanding the Inner Workings of Language Models Through Representation Dissimilarity

October 23, 2023 ยท Declared Dead ยท ๐Ÿ› Conference on Empirical Methods in Natural Language Processing

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Davis Brown, Charles Godfrey, Nicholas Konz, Jonathan Tu, Henry Kvinge arXiv ID 2310.14993 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.CL Citations 13 Venue Conference on Empirical Methods in Natural Language Processing Last Checked 5 months ago
Abstract
As language models are applied to an increasing number of real-world applications, understanding their inner workings has become an important issue in model trust, interpretability, and transparency. In this work we show that representation dissimilarity measures, which are functions that measure the extent to which two model's internal representations differ, can be a valuable tool for gaining insight into the mechanics of language models. Among our insights are: (i) an apparent asymmetry in the internal representations of model using SoLU and GeLU activation functions, (ii) evidence that dissimilarity measures can identify and locate generalization properties of models that are invisible via in-distribution test set performance, and (iii) new evaluations of how language model features vary as width and depth are increased. Our results suggest that dissimilarity measures are a promising set of tools for shedding light on the inner workings of language models.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted