Neural-network building blocks · MLD-1029
Residual stream
The evolving representation to which residual blocks contribute updates.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Track token states across Transformer layers.
Original caveat
Features may be distributed across many coordinates.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Theory.
Tags: DL · SLM · LLM · Vision · NLP.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗