What is Positional Encoding? Why does it exist? Where does it appear in Positional Information?
Draw or describe a visual model of Positional Encoding. What does it look like conceptually?
Work through a concrete manual example of Positional Encoding with real numbers or pseudocode.
How is Positional Encoding different from related concepts in Positional Information? What are the trade-offs?
Explain Positional Encoding in plain language using an analogy. Could a non-expert follow it?
tiny_llm/transformer.py
📋 full plan →