Sep 17, 2024
Latent Space Clustering and Summarization
Matthew Shinkle
I wanted to see how modern dimensionality reduction and clustering approaches can support visualization and interpretation of LLM latent spaces. I explored a number of different approaches and algoriths, but ultimately converged on UMAP for dimensionality reduction and birch clustering to extract groups of tokens in the latent space of a layer.
No reviews are available yet
Cite this work
@misc {
title={
@misc {
},
author={
Matthew Shinkle
},
date={
9/17/24
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}