# Dimension

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: dimensions, dimensionality, embedding dimension, vector size

One number position in a [vector](https://ecosystem.samcarlton.com/vector), like one axis on a map. An [embedding](https://ecosystem.samcarlton.com/embedding) with 1,024 dimensions describes each item with 1,024 numbers. More dimensions can capture finer distinctions but cost more to store and search.

**For example:** A map has two dimensions, east-west and north-south. An [embedding](https://ecosystem.samcarlton.com/embedding) is a map with hundreds of dimensions instead.

## Connects to (5)

- [Vector](https://ecosystem.samcarlton.com/vector): An ordered list of numbers.
- [Embedding](https://ecosystem.samcarlton.com/embedding): A way of turning a piece of text into a list of numbers that captures its meaning, so software can tell which pieces of text are about…
- [Latent space](https://ecosystem.samcarlton.com/latent-space): The internal map of numbers where a model places the things it reads.
- [Vector database](https://ecosystem.samcarlton.com/vector-database): A database built to store embeddings and quickly find the items closest in meaning to a question, not just the ones that share its exact…
- [Cosine similarity](https://ecosystem.samcarlton.com/cosine-similarity): A common way to measure how alike two vectors are by the angle between them.

Map view: https://ecosystem.samcarlton.com/dimension