# A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models

arXiv: https://arxiv.org/abs/2407.02646 · HTML: https://mlsanity.com/paper/2407.02646/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- Placed in Circuits and mechanistic analysis, one of 13 directions in Mechanistic interpretability.
- Builds on 142 of its 196 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Placed in

- Mechanistic interpretability / [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/)

## Builds on (most cited first, 30 of 142)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)

## Built on by (most cited first, 30 of 118)

- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [Agentic Large Language Models, a survey](https://mlsanity.com/paper/2503.23037/) (2025)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2410.22366/) (2024)
- [Mitigating Overthinking in Large Reasoning Models via Manifold Steering](https://mlsanity.com/paper/2505.22411/) (2025)
- [How do LLMs Compute Verbal Confidence](https://mlsanity.com/paper/2603.17839/) (2026)
- [Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions](https://mlsanity.com/paper/2505.17120/) (2025)
- [SAE-V: Interpreting Multimodal Models for Enhanced Alignment](https://mlsanity.com/paper/2502.17514/) (2025)
- [The Geometry of Reasoning: Flowing Logics in Representation Space](https://mlsanity.com/paper/2510.09782/) (2025)
- [Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis](https://mlsanity.com/paper/2502.11812/) (2025)
- [Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism](https://mlsanity.com/paper/2504.18574/) (2025)
- [Layers at Similar Depths Generate Similar Activations Across LLM Architectures](https://mlsanity.com/paper/2504.08775/) (2025)
- [Distributional AGI Safety](https://mlsanity.com/paper/2512.16856/) (2025)
- [Large Language Models as Proxies for Theories of Human Linguistic Cognition](https://mlsanity.com/paper/2502.07687/) (2025)
- [Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates](https://mlsanity.com/paper/2505.10039/) (2025)
- [Do Activation Verbalization Methods Convey Privileged Information?](https://mlsanity.com/paper/2509.13316/) (2025)
- [Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs](https://mlsanity.com/paper/2510.13251/) (2025)
- [The underlying structures of self-attention: symmetry, directionality, and emergent dynamics in Transformer training](https://mlsanity.com/paper/2502.10927/) (2025)
- [A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations](https://mlsanity.com/paper/2507.23221/) (2025)
- [Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models](https://mlsanity.com/paper/2509.17588/) (2025)
- [An explainable transformer circuit for compositional generalization](https://mlsanity.com/paper/2502.15801/) (2025)
- [VLAs are Confined yet Capable of Generalizing to Novel Instructions](https://mlsanity.com/paper/2505.03500/) (2025)
- [CLUE: Conflict-guided Localization for LLM Unlearning Framework](https://mlsanity.com/paper/2509.20977/) (2025)
- [Large Language Models as Computable Approximations to Solomonoff Induction](https://mlsanity.com/paper/2505.15784/) (2025)
- [Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks](https://mlsanity.com/paper/2511.19265/) (2025)
- [Interpretability for Time Series Transformers using A Concept Bottleneck Framework](https://mlsanity.com/paper/2410.06070/) (2024)
- [Electronic Circuit Principles of Large Language Models](https://mlsanity.com/paper/2502.03325/) (2025)
- [CoCo-CoLa: Evaluating and Improving Language Adherence in Multilingual LLMs](https://mlsanity.com/paper/2502.12476/) (2025)
- [LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades](https://mlsanity.com/paper/2505.13515/) (2025)

## Abstract (arXiv)

Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for interpreting transformer-based language models (LMs), resulting in many novel insights yet introducing new challenges. However, there has not been work that comprehensively reviews these insights and challenges, particularly as a guide for newcomers to this field. To fill this gap, we provide a comprehensive survey from a task-centric perspective, organizing the taxonomy of MI research around specific research questions or tasks. We outline the fundamental objects of study in MI, along with the techniques, evaluation methods, and key findings for each task in the taxonomy. In particular, we present a task-centric taxonomy as a roadmap for beginners to navigate the field by helping them quickly identify impactful problems in which they are most interested and leverage MI for their benefit. Finally, we discuss the current gaps in the field and suggest potential future directions for MI research.