Category: Sparse Autoencoder
-
Neural Networks Are Blurry, Symbolic Systems Are Fragmented. Sparse Autoencoders Help Us Combine Them.
Neural Networks Are Blurry, Symbolic Systems Are Fragmented. Sparse Autoencoders Help Us Combine Them. Neural and symbolic models compress the world in fundamentally different ways, and Sparse Autoencoders (SAEs) offer a bridge to connect them. The post Neural Networks Are Blurry, Symbolic Systems Are Fragmented. Sparse Autoencoders Help Us Combine Them. appeared first on Towards…
-
Formulation of Feature Circuits with Sparse Autoencoders in LLM
Formulation of Feature Circuits with Sparse Autoencoders in LLM Large Language models (LLMs) have witnessed impressive progress and these large models can do a variety of tasks, from generating human-like text to answering questions. However, understanding how these models work still remains challenging, especially due a phenomenon called superposition where features are mixed into one…