# NEAT: Concept driven Neuron Attribution in LLMs

arXiv: https://arxiv.org/abs/2508.15875 · HTML: https://mlsanity.com/paper/2508.15875/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 21 Aug 2025.

## Builds on (most cited first, 15 of 15)

- [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)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning](https://mlsanity.com/paper/2305.14160/) (2023)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [Localizing Model Behavior with Path Patching](https://mlsanity.com/paper/2304.05969/) (2023)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [Future Lens: Anticipating Subsequent Tokens from a Single Hidden State](https://mlsanity.com/paper/2311.04897/) (2023)
- [Interpretability at Scale: Identifying Causal Mechanisms in Alpaca](https://mlsanity.com/paper/2305.08809/) (2023)
- [Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps](https://mlsanity.com/paper/2307.05052/) (2023)
- [IndiBias: A Benchmark Dataset to Measure Social Biases in Language Models for Indian Context](https://mlsanity.com/paper/2403.20147/) (2024)
- [Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT](https://mlsanity.com/paper/2402.12201/) (2024)
- [VisQA: X-raying Vision and Language Reasoning in Transformers](https://mlsanity.com/paper/2104.00926/) (2021)

## Built on by (most cited first, 1 of 1)

- [GKnow: Measuring the Entanglement of Gender Bias and Factual Gender](https://mlsanity.com/paper/2605.12299/) (2026)

## Abstract (arXiv)

Locating neurons that are responsible for final predictions is important for opening the black-box large language models and understanding the inside mechanisms. Previous studies have tried to find mechanisms that operate at the neuron level but these methods fail to represent a concept and there is also scope for further optimization of compute required. In this paper, with the help of concept vectors, we propose a method for locating significant neurons that are responsible for representing certain concepts and term those neurons as concept neurons. If the number of neurons is n and the number of examples is m, we reduce the number of forward passes required from O(n*m) to just O(n) compared to the previous works and hence optimizing the time and computation required over previous works. We also compare our method with several baselines and previous methods and our results demonstrate better performance than most of the methods and are more optimal when compared to the state-of-the-art method. We, as part of our ablation studies, also try to optimize the search for the concept neurons by involving clustering methods. Finally, we apply our methods to find, turn off the neurons that we find, and analyze its implications in parts of hate speech and bias in LLMs, and we also evaluate our bias part in terms of Indian context. Our methodology, analysis and explanations facilitate understating of neuron-level responsibility for more broader and human-like concepts and also lay a path for future research in this direction of finding concept neurons and intervening them.