📐 AI Vector Similarity Matrix
📐 AI Vector Similarity Matrix
Launcher for the standalone AI: compare two texts by cosine, Euclidean and dot product over 64-dim hashed embeddings, with token overlap, Jaccard and per-dimension sparklines. In-browser.
The similarity bench is a Knowledge-mode instrument of the standalone AI: embed any two texts with the same 64-dimension hashed vectors the retriever uses, and read cosine, L2, dot product, token overlap and the vectors themselves.
Open in the standalone AIOpens at: Knowledge mode → similarity · runs entirely in your browser · no account, no API key, nothing uploaded
What the standalone AI gives you for this
- Cosine, Euclidean and dot product with a plain-language reading
- Per-dimension sparklines for both vectors
- An honest note on what hashed bag-of-words vectors can and cannot see
The interactive tool that used to live on this card now runs inside the standalone AI at ai.html, where it shares your indexed documents, stored memories and every reasoning method. This card stays in the catalogue as a launcher so existing links keep working.