mlsanityData to 7 Oct 2026

Intra-neuronal attention within language models Relationships between activation and semantics

arXiv 2503.12992 ↗First posted 17 Mar 2025cs.AI cs.CL q-bio.NCcited by 0

Not on the map. Why?

Abstract (arXiv)

This study investigates the ability of perceptron-type neurons in language models to perform intra-neuronal attention; that is, to identify different homogeneous categorical segments within the synthetic thought category they encode, based on a segmentation of specific activation zones for the tokens to which they are particularly responsive. The objective of this work is therefore to determine to what extent formal neurons can establish a homomorphic relationship between activation-based and categorical segmentations. The results suggest the existence of such a relationship, albeit tenuous, only at the level of tokens with very high activation levels. This intra-neuronal attention subsequently enables categorical restructuring processes at the level of neurons in the following layer, thereby contributing to the progressive formation of high-level categorical abstractions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 144 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

40 of 144 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  8. 2020Big Bird: Transformers for Longer Sequencescited by 1,673
  9. 2020Reformer: The Efficient Transformercited by 1,658
  10. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  11. 2020Transformer Feed-Forward Layers Are Key-Value Memoriescited by 1,307
  12. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
28 more
  1. 2019What Does BERT Look At? An Analysis of BERT's Attentioncited by 994
  2. 2019Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Prunedcited by 844
  3. 2019Are Sixteen Heads Really Better than One?cited by 803
  4. 2020Efficient Transformers: A Surveycited by 784
  5. 2021Knowledge Neurons in Pretrained Transformerscited by 590
  6. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  7. 2020A Survey of the State of Explainable AI for Natural Language Processingcited by 206
  8. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  9. 2020Generating Fact Checking Explanationscited by 132
  10. 2023A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimationcited by 108
  11. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  12. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  13. 2017Machine learning for neural decodingcited by 45
  14. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  15. 2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
  16. 2022On the Transformation of Latent Space in Fine-Tuned NLP Modelscited by 19
  17. 2023Can LLMs facilitate interpretation of pre-trained language models?cited by 15
  18. 2024Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformerscited by 9
  19. 2023Evaluating Neuron Interpretation Methods of NLP Modelscited by 8
  20. 2024From Cognition to Computation: A Comparative Review of Human Attention and Transformer Architecturescited by 6
  21. 2024Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networkscited by 5
  22. 2023Attention-Enhanced Co-Interactive Fusion Network (AECIF-Net) for Automated Structural Condition Assessment in Visual Inspectioncited by 4
  23. 2024A hierarchical Bayesian model for syntactic primingcited by 4
  24. 2024Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Taskscited by 3
  25. 2024Neuropsychology of AI: Relationship Between Activation Proximity and Categorical Proximity Within Neural Categories of Synthetic Cognitioncited by 3
  26. 2024How Do Artificial Intelligences Think? The Three Mathematico-Cognitive Factors of Categorical Segmentation Operated by Synthetic Neuronscited by 3
  27. 2025The Process of Categorical Clipping at the Core of the Genesis of Concepts in Synthetic Neural Cognitioncited by 3
  28. 2025Synthetic Categorical Restructuring large Or How AIs Gradually Extract Efficient Regularities from Their Experience of the Worldcited by 2

Built on by

Not cited yet.