Receptive Field
The specific region of the input space that a particular neuron or layer in a neural network is exposed to and can draw contextual information from.
Think of It Like This
Like looking through a cardboard tube; you can only see a small circle of the world, and anything outside that circle cannot affect your judgment.
In early layers of a CNN, the receptive field is just a few pixels. As the network gets deeper via pooling and convolutions, neurons gain a much larger receptive field, allowing them to recognize complex structures like faces rather than just edges. In transformers, the self-attention mechanism gives every token a global receptive field immediately.