# Latent space

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

Also called: latent, embedding space, latent representation, vector space, latent spaces

The internal map of numbers where a model places the things it reads. Items with similar meaning land near each other. Another name for it is embedding space.

**For example:** In a model's latent space, 'invoice' and 'bill' sit close together. 'Invoice' and 'giraffe' sit far apart.

## Connects to (8)

- [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…
- [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…
- [Model](https://ecosystem.samcarlton.com/model): The trained system at the center of an AI product.
- [Parameters](https://ecosystem.samcarlton.com/parameters): The values a model learns during training.
- [Vector](https://ecosystem.samcarlton.com/vector): An ordered list of numbers.
- [Dimension](https://ecosystem.samcarlton.com/dimension): One number position in a vector, like one axis on a map.
- [Attention](https://ecosystem.samcarlton.com/attention): The part of a language model that decides, for each token, how much every other token in the input should shape its meaning.
- [Interpretability](https://ecosystem.samcarlton.com/interpretability): Research into what is happening inside an AI model: which internal patterns represent which ideas and how they lead to an output.

Map view: https://ecosystem.samcarlton.com/latent-space