# Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism

arXiv: https://arxiv.org/abs/2310.16270 · HTML: https://mlsanity.com/paper/2310.16270/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 13 of 13)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [PMET: Precise Model Editing in a Transformer](https://mlsanity.com/paper/2308.08742/) (2023)
- [The Hydra Effect: Emergent Self-repair in Language Model Computations](https://mlsanity.com/paper/2307.15771/) (2023)
- [Analyzing Transformers in Embedding Space](https://mlsanity.com/paper/2209.02535/) (2022)
- [Backdoor Attacks for In-Context Learning with Language Models](https://mlsanity.com/paper/2307.14692/) (2023)
- [Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models](https://mlsanity.com/paper/2309.05605/) (2023)

## Built on by (most cited first, 22 of 22)

- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models](https://mlsanity.com/paper/2407.02646/) (2024)
- [Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models](https://mlsanity.com/paper/2402.18154/) (2024)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [Finding Transformer Circuits with Edge Pruning](https://mlsanity.com/paper/2406.16778/) (2024)
- [A Concept-Based Explainability Framework for Large Multimodal Models](https://mlsanity.com/paper/2406.08074/) (2024)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs](https://mlsanity.com/paper/2407.19200/) (2024)
- [JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit](https://mlsanity.com/paper/2411.11114/) (2024)
- [Head Pursuit: Probing Attention Specialization in Multimodal Transformers](https://mlsanity.com/paper/2510.21518/) (2025)
- [Analyzing Finetuning Representation Shift for Multimodal LLMs Steering](https://mlsanity.com/paper/2501.03012/) (2025)
- [Decoupling Positional and Symbolic Attention Behavior in Transformers](https://mlsanity.com/paper/2511.11579/) (2025)
- [Trillion Parameter AI Serving Infrastructure for Scientific Discovery: A Survey and Vision](https://mlsanity.com/paper/2402.03480/) (2024)
- [Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures](https://mlsanity.com/paper/2509.25045/) (2025)
- [Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2603.18523/) (2026)
- [Legible-by-Construction: Attention and End-to-End Transformers](https://mlsanity.com/paper/2607.04319/) (2026)
- [Universal Response and Emergence of Induction in LLMs](https://mlsanity.com/paper/2411.07071/) (2024)
- [Training, Reading, and Editing Legible Transformers](https://mlsanity.com/paper/2607.08946/) (2026)
- [InTraVisTo: Inside Transformer Visualisation Tool](https://mlsanity.com/paper/2507.13858/) (2025)
- [Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document](https://mlsanity.com/paper/2509.26235/) (2025)
- [KA2L: A Knowledge-Aware Active Learning Framework for LLMs](https://mlsanity.com/paper/2603.17566/) (2026)
- [Interpreting Language Model Hidden States at Scale](https://mlsanity.com/paper/2608.10260/) (2026)

## Abstract (arXiv)

Transformer-based Large Language Models (LLMs) are the state-of-the-art for natural language tasks. Recent work has attempted to decode, by reverse engineering the role of linear layers, the internal mechanisms by which LLMs arrive at their final predictions for text completion tasks. Yet little is known about the specific role of attention heads in producing the final token prediction. We propose Attention Lens, a tool that enables researchers to translate the outputs of attention heads into vocabulary tokens via learned attention-head-specific transformations called lenses. Preliminary findings from our trained lenses indicate that attention heads play highly specialized roles in language models. The code for Attention Lens is available at github.com/msakarvadia/AttentionLens.