https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity Don’t use cosine similarity carelesslyPiotr Migdał14 Jan 2025 “…we’ll see that blindly applying cosine similarity to vectors can lead us astray. While embeddings do capture similarities, they often reflect
What I Read: Autoencoders, Interpretability
https://adamkarvonen.github.io/machine_learning/2024/06/11/sae-intuitions.html An Intuitive Explanation of Sparse Autoencoders for LLM InterpretabilityAdam KarvonenJun 11, 2024 “Sparse Autoencoders (SAEs) have recently become popular for interpretability of machine learning models…”
What I Read: Gaussians
https://gestalt.ink/gaussians Understanding Gaussians “The Gaussian distribution, or normal distribution is a key subject in statistics, machine learning, physics, and pretty much any other field that deals with data and probability.”
What I Read: cosine similarity
https://tomhazledine.com/cosine-similarity-alternatives Alternatives to cosine similarityTom Hazledine9/20/24 8:00 PM “Cosine similarity is the recommended way to compare vectors, but what other distance functions are there? And are any of them better?”
What I Read: Transformers Inference Optimization
https://astralord.github.io/posts/transformer-inference-optimization-toolset Transformers Inference Optimization ToolsetAleksandr SamarinOct 1, 2024 “Large Language Models are pushing the boundaries of artificial intelligence, but their immense size poses significant computational challenges. As these models grow,
What I Read: embedding models
https://unstructured.io/blog/understanding-embedding-models-make-an-informed-choice-for-your-rag Understanding embedding models: make an informed choice for your RAGMaria KhalusovaAug 13, 2024 “How do you choose a suitable embedding model for your RAG application?”