Close means two vectors point in a similar direction, or sit near each other. The model has learned that those two tokens are used in similar ways, so it treats them as similar in meaning.
king and queen end up close because they appear in similar contexts; cat and carburetor end up far apart. Close means "used in similar ways", which is not always "means the same" — opposites like hot and cold can end up close. A static embedding gives bank one position for both meanings; a contextual embedding moves it nearer to money or nearer to river, depending on the sentence.
One dimension on its own has no human-readable meaning. Closeness only makes sense when you compare whole vectors.
What is Cosine Similarity? Why does it exist? Where does it appear in Embeddings?
Draw or describe a visual model of Cosine Similarity. What does it look like conceptually?
Work through a concrete manual example of Cosine Similarity with real numbers or pseudocode.
Implement Cosine Similarity from scratch in Python. Keep it minimal — just enough to see it work.
Try Cosine Similarity on a real example. Vary the inputs and observe what changes.
How is Cosine Similarity different from related concepts in Embeddings? What are the trade-offs?
Explain Cosine Similarity in plain language using an analogy. Could a non-expert follow it?
Build a small project or demo that uses Cosine Similarity as a core component.
agent/verifier.py
📋 full plan →