Embeddings & Representations
The lookup table, the residual stream, contextual vectors, geometry and superposition.
11concepts
47flashcards
81minutes of reading
- 01 Cosine Similarity vs Dot Product Two near-identical looking formulas that answer different questions, one measures direction alone, the other measures direction and magnitude together, and picking the wrong one silently breaks a search or ranking system.
- 02 Embeddings and Semantic Search How dense vectors turn text into a geometry of meaning, and how cosine similarity lets you find related content without keywords.
- 03 Input Embeddings and the Lookup Table How a token id becomes a vector, a single row lookup into a trained matrix, and why that matrix is often the largest single block of parameters a small model spends before any real computation happens.
- 04 word2vec and GloVe The two ideas, predict-a-neighbour and factor-a-co-occurrence-matrix, that first proved dense vectors could capture enough word meaning to support arithmetic on it, years before transformers existed.
- 05 Sentence Embeddings and Pooling A transformer produces one vector per token, not one per sentence, so turning a sequence of contextual vectors into a single comparable vector requires a pooling choice that quietly changes what "similar" ends up meaning.
- 06 Static vs Contextual Embeddings The shift from one vector per word to one vector per word-in-context, and why that shift is arguably the single biggest reason transformer-based models outperformed earlier NLP.
- 07 Weight Tying of Input and Output Embeddings Why most language models score every candidate next token using the transpose of the exact same matrix that looked up the input tokens, cutting parameters and improving perplexity in one move.
- 08 Embedding Geometry and Anisotropy Learned embedding spaces are not the well-spread sphere the geometric intuition suggests, they collapse into a narrow cone, and that fact quietly breaks naive similarity comparisons built on top of them.
- 09 Superposition and Polysemantic Neurons Individual neurons in a trained network routinely fire for several unrelated concepts at once, and the leading explanation is not noise, it is a model deliberately packing more features than it has dimensions using near-orthogonal directions.
- 10 The Residual Stream Reframing a transformer's residual connections as one shared, additive vector space that every layer reads from and writes to, the lens that makes attention, MLPs, and interpretability results legible as a single system.
- 11 Unembedding and the Logit Lens Multiplying an intermediate layer's residual stream by the final unembedding matrix, as if it were the last layer, turns out to produce surprisingly sensible next-token guesses, a cheap window into what a model has committed to mid-computation.