Work

Visualizing Attention in Transformer-Based Language models

Year: 2019
Type: preprint
Abstract: We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can help to interpret the model, and we demonstrate the tool on the BERT model and the OpenAI GPT-2 model. We also present three use cases for analyzing GPT-2: detecting model bias, identifying recurring patterns, and linking neurons to model behavior.
Author: Jesse Vig
Language: English
Open Access status: green
OpenAlex ID: W2934032625
Cites: 3
Cited by: 20
Related to: 10