one fable-low hijack cell
pair embedding / gradient
envelope en_arrow
ordering BA
effort low
English with arrow '→' — '{X} → {Y}'
verdictpicked embedding (first-offered)
· classifierA
· tiernone
response (200 chars)
# Gradient Flow into Embedding Layers
## The Setup
An embedding layer is just a lookup table: a matrix **E** of shape `(vocab_size, dim)`. A token id `i` selects row `E[i]`.
```
token id → E[i] → do
neighbors