Easy Embeddings Question 7 of 223

What does cosine similarity measure for embeddings?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

PICTURE THIS: 1, 2, 2, 8

Mean3.25average

Median2middle

Mode2most often

Simple meaning

Cosine similarity measures the angle between two vectors, not their raw length.

WHY — Tokens instead of words?

LLMs use tokens (not full words) because it helps them:

Embeddings questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

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:

1
Cosine similarity measures the
angle between two vectors, not their raw length.
2
Values near 1 mean
the directions align, so the items are treated as similar.
3
It is the usual
score for comparing normalized text embeddings.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
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):

Input text

“Values near 1 mean the directions align, so the items are treated as similar.”

Tokenized output

Valuesnear1meanthedirections

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Key takeaway

Cosine similarity measures the angle between two vectors, not their raw length. Values near 1 mean the directions align, so the items are treated as similar.