paper-with-me

홈 › Papers

Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps

2023-02-01 · Goro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui

Transformers are ubiquitous in wide tasks. Interpreting their internals is a pivotal goal. Nevertheless, their particular components, feed-forward (FF) blocks, have typically been less analyzed despite their substantial parameter amounts. We analyze the input contextualization effects of FF blocks by rendering them in the attention maps as a human-friendly visualization scheme. Our experiments with both masked- and causal-language models reveal that FF networks modify the input contextualization to emphasize specific types of linguistic compositions. In addition, FF and its surrounding components tend to cancel out each other's effects, suggesting potential redundancy in the processing of the Transformer layer.

📄 PDF Abstract BibTeX arXiv:2302.00456

Code (1)

gorokoba560/norm-analysis-of-transformer 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Position-Wise Feed-Forward Layer 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…
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 $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Neural ODE Transformers: Analyzing Internal Dynamics and Adaptive Fine-tuning

2025-03-03 · Anh Tong, Thanh Nguyen-Tang, Dongeun Lee, Duc Nguyen 외

Recent advancements in large language models (LLMs) based on transformer architectures have sparked significant interest in understanding their inner workings. In this paper, we introduce a novel approach to modeling tra…

Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers

2024-07-16 · Freya Behrens, Luca Biggio, Lenka Zdeborová

Next to scaling considerations, architectural design choices profoundly shape the solution space of transformers. In this work, we analyze the solutions simple transformer blocks implement when tackling the histogram tas…

Memorization

Brainformers: Trading Simplicity for Efficiency

2023-05-29 · Yanqi Zhou, Nan Du, Yanping Huang, Daiyi Peng 외

Transformers are central to recent successes in natural language processing and computer vision. Transformers have a mostly uniform backbone where layers alternate between feed-forward and self-attention in order to buil…

Interpretability in Activation Space Analysis of Transformers: A Focused Survey

2023-01-22 · Soniya Vijayakumar

The field of natural language processing has reached breakthroughs with the advent of transformers. They have remained state-of-the-art since then, and there also has been much research in analyzing, interpreting, and ev…

Survey

The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training

2025-02-26 · Jinbo Wang, Mingze Wang, Zhanpeng Zhou, Junchi Yan 외

Transformers consist of diverse building blocks, such as embedding layers, normalization layers, self-attention mechanisms, and point-wise feedforward networks. Thus, understanding the differences and interactions among …

Language ModelingLanguage ModellingLarge Language Model