nowfound

Life & fun · November 29, 2023

IM

I made a 3D visual "thesaurus" for English

Just a fun toy I wanted to make. I've been studying and playing around with language models lately and have always been intrigued by how words are processed by these models. Since the vectors generated by embedding models is in very high dimensional space, I thought it would be cool to reduce them to 3D vectors and visualise them myself. This is what I have so far!

I made a 3D visual "thesaurus" for English launched on November 29, 2023 with 19 votes, #1,286 of 4,332 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 2 years on.

Visit seesaurus.com ↗Alternatives

In plain words

This project visualizes English words in three-dimensional space by converting high-dimensional word embeddings from language models into interactive 3D representations. It functions as a visual thesaurus where users can explore how words relate to each other spatially, based on how machine learning models understand semantic similarity. Created as an experimental exploration of language model mechanics, it offers an intuitive way to see word relationships that would otherwise exist in abstract mathematical space.

written from the facts on this page · September 2026

Does a similar job

all alternatives →
  • Semantic Calculator (king-man+woman=?)2025 · calc.datova.ai · ▲176

    I've been playing with embeddings and wanted to try out what results the embedding layer will produce based on just word-by-word input and addition / subtraction, beyond what many videos / papers mention (like the obvious king-man+woman=queen). So I built something that doesn't just give the first answer, but ranks the matches based on distance / cosine symmetry. I polished it a bit so that others can try it out, too. For now, I only have nouns (and some proper nouns) in the dataset, and pick the most common interpretation among the homographs. Also, it's case sensitive.

  • 3W
    3d Word Vectors with Neural Networks, T-SNE, and WebGL2013 · wordcloud.ersatz1.com · ▲30
  • IM
    I made a website to semantically search ArXiv papers2024 · papermatch.mitanshu.tech · ▲324

    As a grad student (and an ADHDer), I had trouble doing literature review systematically. To combat this, I made a website that finds similar papers using the meaning of the thing I am looking for. I used MixedBread's [^1] embedding model to generate vectors from the abstracts. I store and search similar vectors using Milvus [^2] and finally use Gradio [^3] to serve the frontend. I update the vector database weekly by pulling the metadata dataset from Kaggle [^4]. To speed up the search process on my free oracle instance, I binarise the embeddings and use Hamming distance as a metric. I would…

  • Fully client-side GPT2 prediction visualizer2023 · perplexity.vercel.app · ▲153

    Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…

  • We fingerprinted 178 AI models' writing styles and similarity clustersApr 2026 · rival.tips · ▲78

    We have a dataset of 3,095 standardized AI responses across 43 prompts. From each response, we extract a 32-dimension stylometric fingerprint (lexical richness, sentence structure, punctuation habits, formatting patterns, discourse markers). Some findings: - 9 clone clusters (>90% cosine similarity on z-normalized feature vectors) - Mistral Large 2 and Large 3 2512 score 84.8% on a composite metric combining 5 independent signals - Gemini 2.5 Flash Lite writes 78% like Claude 3 Opus. Costs 185x less - Meta has the strongest provider "house style" (37.5x distinctiveness ratio) - "Satirical…

  • WT
    Word Tree in D3.js2013 · jasondavies.com · ▲158

More life & fun this month

the category →

Source: Show HN post ↗

Launched alongside, November 2023

the whole month →
  • Flowla▲1,119

    Digital sales rooms that wow buyers

    Growth · 2023 · flowla.com

  • Passionfroot Discovery▲962

    Discover & book top creators to promote your product

    Growth · 2023 · passionfroot.me

  • Re:catch▲939

    If Google Form & Calendly had a baby

    Growth · 2023 · recatch.cc

  • Pitch 2.0▲886

    Create, share and analyze presentations faster than ever

    Work · 2023 · pitch.com

  • LeadDelta 3.0▲883

    CRM built for modern teams & creators powered by AI

    AI · 2023 · leaddelta.com

  • SpeedVitals▲829

    Hi HN, I’m Kashish, one of the co-founders of SpeedVitals, a platform for testing & monitoring website performance with a major emphasis on Core Web Vitals. Until now, our platform has only focused on Synthetic/Lab testing, such as Lighthouse tests and TTFB tests. But now, we have developed a Real-User Monitoring platform that doubles up as a Web Analytics tool. One major feature we have that most RUM tools lack is Performance Audits. Just like Lighthouse audits work on Lab test data, our audits work across all the real-user visits and gives suggestions on what task to prioritize first.…

    Dev tools · 2023 · speedvitals.com