Series Expedition
Large Language Models
Explore the inside of large language models through embedding space, self-attention, the residual stream, and next-token prediction as near-future 3D spaces.
Machine-translated from the English original.
सुझाया गया रास्ता
एक ऐसा क्रम चलें जो उसी विषय पर क्रमशः गहरी दृष्टियों को जोड़ता है।
1/4 · उपलब्धEmbedding Nebula
Project tokens into a 3D semantic nebula and trace vector arithmetic such as king − man + woman ≈ queen.
2/4 · उपलब्धAttention Beams
Visualize self-attention as a web of beams between tokens and test the weights from softmax(QKᵀ/√dk).
3/4 · उपलब्धResidual Stream
Follow the residual stream as a luminous river where each layer writes and reads information.
4/4 · उपलब्धNext-token Prediction
Watch logits become a probability distribution through softmax and change shape with temperature before converging on one token.