Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
Reviewed by Pithpith:NHE6LKZ2open to challenge →
read the original abstract
Transformer networks have revolutionized NLP representation learning since they were introduced. Though a great effort has been made to explain the representation in transformers, it is widely recognized that our understanding is not sufficient. One important reason is that there lack enough visualization tools for detailed analysis. In this paper, we propose to use dictionary learning to open up these "black boxes" as linear superpositions of transformer factors. Through visualization, we demonstrate the hierarchical semantic structures captured by the transformer factors, e.g., word-level polysemy disambiguation, sentence-level pattern formation, and long-range dependency. While some of these patterns confirm the conventional prior linguistic knowledge, the rest are relatively unexpected, which may provide new insights. We hope this visualization tool can bring further knowledge and a better understanding of how transformer networks work. The code is available at https://github.com/zeyuyun1/TransformerVis
This paper has not been read by Pith yet.
Forward citations
Cited by 8 Pith papers
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reason...
-
Scaling and evaluating sparse autoencoders
K-sparse autoencoders with dead-latent fixes produce clean scaling laws and better feature quality metrics that improve with size, shown by training a 16-million-latent model on GPT-4 activations.
-
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
Sparse autoencoders scaled to 34 million features on Claude 3 Sonnet yield interpretable, steerable representations of concrete and abstract concepts that generalize across languages and modalities.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-sou...
-
Sparse Autoencoders Find Highly Interpretable Features in Language Models
Sparse autoencoders applied to language model activations yield more interpretable and monosemantic features than alternative approaches, enabling finer causal analysis on the indirect object identification task.
-
Steered Generation via Gradient-Based Optimization on Sparse Query Features
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
-
REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
REFLEX improves explainable fact-checking by using verdict-anchored style control and self-disagreement signals to disentangle fact from style in LLM outputs, achieving SOTA results with minimal self-refined samples.
-
Principles and Practice of Deep Representation Learning: or a Mathematical Theory of Memory
The book presents principles from optimization and information theory to explain deep network architectures and enable new interpretable models.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.