ansonyuu/matchmaking: Embedding space of names clustered based on their interests using the sentence-transformers all-MiniLM-L6-v2 model

Embedding space of names clustered based on their interests using the sentence-transformers all-MiniLM-L6-v2 model

"Words can't describe how unique your interests are... but coordinates can" - Sean Ashley, circa 2023 A flattened embedding space of names clustered based on their interests using the sentence-transformers all-MiniLM-L6-v2 model. Created for the UW Startups S23 Kickoff event with guidance from Jacky Zhao and Sean Ashley. Simha Kalimipalli later aded interactivity! Instructions for use Collect or format your data in the following format Name What are your interests? (or varying permutations of this question) Alice I love being the universal placeholder for every CS joke ever Bob I too…

saved by

• Linda
• Yesh Chala

related reading

• GitHub - harvardnlp/annotated-transformer: An annotated implementation of the Transformer paper. · GitHubgithub.com
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
• The Annotated Transformernlp.seas.harvard.edu
• Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
• the-algorithm/src/scala/com/twitter/simclusters_v2/README.md at main · twitter/the-algorithmgithub.com
• Embeddings: What they are and why they mattersimonwillison.net
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
• Matryoshka Sparse Autoencoders — LessWronglesswrong.com
• A gentle introduction to sparse autoencoders — LessWronglesswrong.com
• Announcing ScaNN: Efficient Vector Similarity Searchai.googleblog.com
• Ranking YC Companies with a Neural Netevjang.com
• GitHub - PaulPauls/llama3_interpretability_sae: A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.github.com