GPT-2 Through the Lens of Vector Symbolic Architectures

NeurIPS 2024 Workshop ATTRIB Submission49 Authors

Release Opt Out: No, I don't wish to opt out of paper release. My paper should be released.

Keywords: transformers, mechanistic interpretability, vector symbolic architectures, sparse autoencoders

Abstract: Understanding the general priniciples behind transformer models remains a complex endeavor. Experiments with probing and disentangling features using sparse autoencoders (SAE) suggest that these models might manage linear features embedded as directions in the residual stream. This paper explores the resemblance between decoder-only transformer architecture and vector symbolic architectures (VSA) and presents experiments indicating that GPT-2 uses mechanisms involving nearly orthogonal vector bundling and binding operations similar to VSA for computation and communication between layers. It further shows that these principles help explain a significant portion of the actual neural weights.

Submission Number: 49