harkous/embeddingsviz
Visualize word embeddings of a vocabulary in TensorBoard, including the neighbors
This tool helps researchers and data scientists visualize word relationships in large language models by creating interactive 3D plots in TensorBoard. You provide a large word embeddings file (like GloVe) and a list of specific words you're interested in, and it outputs a curated visualization showing those words and their closest neighbors. This is ideal for anyone exploring the semantic space of words.
No commits in the last 6 months.
Use this if you need to visually explore the relationships between a specific subset of words in a large word embedding model without TensorBoard becoming too slow.
Not ideal if you want to visualize every single word in an extremely large vocabulary, as it focuses on visualizing a selected subset and their neighbors for performance.
Stars
46
Forks
8
Language
Python
License
MIT
Category
Last pushed
Jul 18, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/harkous/embeddingsviz"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cosmosgl/graph
GPU-accelerated force graph layout and rendering
Clay-foundation/model
The Clay Foundation Model - An open source AI model and interface for Earth
nomic-ai/nomic
Nomic Developer API SDK
omoindrot/tensorflow-triplet-loss
Implementation of triplet loss in TensorFlow
sashakolpakov/dire-jax
DImensionality REduction in JAX