paper-with-me

홈 › Papers

GPT-2 Through the Lens of Vector Symbolic Architectures

2024-12-10 · Johannes Knittel, Tushaar Gangavarapu, Hendrik Strobelt, Hanspeter Pfister

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.

📄 PDF Abstract BibTeX arXiv:2412.07947

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder

2025-06-25 · Yingji Zhang, Danilo S. Carvalho, André Freitas

Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto…

Representation Learning

Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures

2024-01-29 · Michael Hersche, Francesco Di Stefano, Thomas Hofmann, Abu Sebastian 외

Abstract reasoning is a cornerstone of human intelligence, and replicating it with artificial intelligence (AI) presents an ongoing challenge. This study focuses on efficiently solving Raven's progressive matrices (RPM),…

Attribute

Bridge Networks: Relating Inputs through Vector-Symbolic Manipulations

2021-06-15 · Wilkie Olin-Ammentorp, Maxim Bazhenov

Despite rapid progress, current deep learning methods face a number of critical challenges. These include high energy consumption, catastrophic forgetting, dependance on global losses, and an inability to reason symbolic…

SymFlux: deep symbolic regression of Hamiltonian vector fields

2025-07-08 · M. A. Evangelista-Alvarado, P. Suárez-Serrato arxiv

We present SymFlux, a novel deep learning framework that performs symbolic regression to identify Hamiltonian functions from their corresponding vector fields on the standard symplectic plane. SymFlux models utilize hybr…

A Walsh Hadamard Derived Linear Vector Symbolic Architecture

2024-10-30 · Mohammad Mahmudul Alam, Alexander Oberle, Edward Raff, Stella Biderman 외

Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are `bound' together to produce a new vector in the same space. VSAs support the commutativity an…

Computational Efficiency