What is cosine similarity for?
PICTURE THIS: AN LLM TURN
Simple meaning
Measuring angle between vectors — common for nearest neighbor search.
WHY — Tokens instead of words?
LLMs use tokens (not full words) because it helps them:
who only read docs from people who shipped.
and tied to GenAI / LLM work.
Each piece maps to a number the network can learn.
Fixed pieces are what transformers expect as input.
STEPS — What happens with tokens?
Before the model can read a sentence, it goes through these steps:
- 1Measuring angle between vectors
— common for nearest neighbor search.
- 2Magnitude differences matter less
than direction.
- 3Embeddings
Normalized embeddings simplify it.
- 4Context mix
Attention looks at nearby tokens together.
- 5Next token
The model scores what should come next.
- 6Decode
IDs turn back into readable text.
EXAMPLE — See it in action
Let's see how a real sentence is tokenized (tokens may vary by model):
Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).
Key takeaway
Measuring angle between vectors — common for nearest neighbor search. Magnitude differences matter less than direction.