Inner Products Measure Alignment in Attention
Compute a dot product, read its sign and magnitude geometrically, and see how query-key scores become attention weights.
Tag
2articleswith this tag.
Compute a dot product, read its sign and magnitude geometrically, and see how query-key scores become attention weights.
Scale and combine vectors, inspect every coordinate in NumPy, and see why attention outputs are a special kind of weighted representation.