# What does the Knowledge Neuron Thesis Have to do with Knowledge?

arXiv: https://arxiv.org/abs/2405.02421 · HTML: https://mlsanity.com/paper/2405.02421/

## Key facts

- Cited by 49 papers in the map (data through 7 Oct 2026).
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 3 May 2024.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [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)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [BLiMP: The Benchmark of Linguistic Minimal Pairs for English](https://mlsanity.com/paper/1912.00582/) (2019)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models](https://mlsanity.com/paper/2301.04213/) (2023)
- [Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models](https://mlsanity.com/paper/2106.06087/) (2021)
- [Interpretability at Scale: Identifying Causal Mechanisms in Alpaca](https://mlsanity.com/paper/2305.08809/) (2023)
- [Analyzing Individual Neurons in Pre-trained Language Models](https://mlsanity.com/paper/2010.02695/) (2020)
- [Rigorously Assessing Natural Language Explanations of Neurons](https://mlsanity.com/paper/2309.10312/) (2023)
- [Characterizing Intrinsic Compositionality in Transformers with Tree Projections](https://mlsanity.com/paper/2211.01288/) (2022)

## Built on by (most cited first, 30 of 49)

- [Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models](https://mlsanity.com/paper/2408.10189/) (2024)
- [Knowledge Circuits in Pretrained Transformers](https://mlsanity.com/paper/2405.17969/) (2024)
- [NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning](https://mlsanity.com/paper/2412.12497/) (2024)
- [Can Knowledge Editing Really Correct Hallucinations?](https://mlsanity.com/paper/2410.16251/) (2024)
- [MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model](https://mlsanity.com/paper/2406.11193/) (2024)
- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (2024)
- [Can Editing LLMs Inject Harm?](https://mlsanity.com/paper/2407.20224/) (2024)
- [LLM-Generated Black-box Explanations Can Be Adversarially Helpful](https://mlsanity.com/paper/2405.06800/) (2024)
- [Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing](https://mlsanity.com/paper/2410.07054/) (2024)
- [Has this Fact been Edited? Detecting Knowledge Edits in Language Models](https://mlsanity.com/paper/2405.02765/) (2024)
- [Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information](https://mlsanity.com/paper/2502.14258/) (2025)
- [Knowledge Localization: Mission Not Accomplished? Enter Query Localization!](https://mlsanity.com/paper/2405.14117/) (2024)
- [Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity](https://mlsanity.com/paper/2407.03779/) (2024)
- [UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models](https://mlsanity.com/paper/2505.20154/) (2025)
- [The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces](https://mlsanity.com/paper/2410.13194/) (2024)
- [Natural Language Processing RELIES on Linguistics](https://mlsanity.com/paper/2405.05966/) (2024)
- [Generalisation First, Memorisation Second? Memorisation Localisation for Natural Language Classification Tasks](https://mlsanity.com/paper/2408.04965/) (2024)
- [Context-Parametric Inversion: Why Instruction Finetuning Can Worsen Context Reliance](https://mlsanity.com/paper/2410.10796/) (2024)
- [All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs](https://mlsanity.com/paper/2605.12671/) (2026)
- [Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs](https://mlsanity.com/paper/2505.09338/) (2025)
- [COMPKE: Complex Question Answering under Knowledge Editing](https://mlsanity.com/paper/2506.00829/) (2025)
- [The Knowledge Microscope: Features as Better Analytical Lenses than Neurons](https://mlsanity.com/paper/2502.12483/) (2025)
- [How Well Can Knowledge Edit Methods Edit Perplexing Knowledge?](https://mlsanity.com/paper/2406.17253/) (2024)
- [Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models](https://mlsanity.com/paper/2502.20408/) (2025)
- [Drop Dropout on Single-Epoch Language Model Pretraining](https://mlsanity.com/paper/2505.24788/) (2025)
- [Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters](https://mlsanity.com/paper/2506.10641/) (2025)
- [Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty](https://mlsanity.com/paper/2511.12991/) (2025)
- [Auditing Language Model Unlearning via Information Decomposition](https://mlsanity.com/paper/2601.15111/) (2026)
- [SHIFT: Gate-Modulated Activation Steering for Knowledge Conflict Mitigation in Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.27786/) (2026)
- [Understanding Language Model Circuits through Knowledge Editing](https://mlsanity.com/paper/2406.17241/) (2024)

## Abstract (arXiv)

We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascent thesis proposes that facts are recalled from the training corpus through the MLP weights in a manner resembling key-value memory, implying in effect that "knowledge" is stored in the network. Furthermore, by modifying the MLP modules, one can control the language model's generation of factual information. The plausibility of the KN thesis has been demonstrated by the success of KN-inspired model editing methods (Dai et al., 2022; Meng et al., 2022). We find that this thesis is, at best, an oversimplification. Not only have we found that we can edit the expression of certain linguistic phenomena using the same model editing methods but, through a more comprehensive evaluation, we have found that the KN thesis does not adequately explain the process of factual expression. While it is possible to argue that the MLP weights store complex patterns that are interpretable both syntactically and semantically, these patterns do not constitute "knowledge." To gain a more comprehensive understanding of the knowledge representation process, we must look beyond the MLP weights and explore recent models' complex layer structures and attention mechanisms.