Image de couverture de livre

Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	He, Zhonghao, Achterberg, Jascha, Collins, Katie, Nejad, Kevin, Akarca, Danyal, Yang, Yinzhu, Gurnee, Wes, Sucholutsky, Ilia, Tang, Yuhan, Ianov, Rebeca, Ogden, George, Li, Chole, Sandbrink, Kai, Casper, Stephen, Ivanova, Anna, Lindsay, Grace W.
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence Neurons and Cognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Principle of Maximum Heterogeneity Optimises Productivity in Distributed Production Systems Across Biology, Economics, and Computing
par: Artis, Guillhem, et autres
Publié: (2026)

Brain-Like Processing Pathways Form in Models With Heterogeneous Experts
par: Cook, Jack, et autres
Publié: (2025)

Spatial embedding promotes a specific form of modularity with low entropy and heterogeneous spectral dynamics
par: Sheeran, Cornelia, et autres
Publié: (2024)

Exploiting heterogeneous delays for efficient computation in low-bit neural networks
par: Sun, Pengfei, et autres
Publié: (2025)

Algorithm-hardware co-design of neuromorphic networks with dual memory pathways
par: Sun, Pengfei, et autres
Publié: (2025)

Language Models Represent Space and Time
par: Gurnee, Wes, et autres
Publié: (2023)

Revisiting Rogers' Paradox in the Context of Human-AI Interaction
par: Collins, Katherine M., et autres
Publié: (2025)

Combatting Gerrymandering with Ranked Choice Voting: An Experimental Analysis of Multi-member Districts in the United States
par: Garg, Nikhil, et autres
Publié: (2021)

Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks
par: Sharma, Jatin, et autres
Publié: (2026)

The Remarkable Robustness of LLMs: Stages of Inference?
par: Lad, Vedang, et autres
Publié: (2024)

Space as Time Through Neuron Position Learning
par: Mészáros, Balázs, et autres
Publié: (2025)

Global topology of human connectome is insensitive to early life environments – A prospective longitudinal study of the general population
par: Sofia Carozza, et autres
Publié: (2024)

Under the Influence: Quantifying Persuasion and Vigilance in Large Language Models
par: Robinson, Sasha, et autres
Publié: (2026)

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
par: Yu, Ziqiao, et autres
Publié: (2025)

Not All Language Model Features Are One-Dimensionally Linear
par: Engels, Joshua, et autres
Publié: (2024)

Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison
par: Yang, Tiancheng, et autres
Publié: (2026)

Learning Human-like Representations to Enable Learning Human Values
par: Wynn, Andrea, et autres
Publié: (2023)

Language Model Teams as Distributed Systems
par: Mieczkowski, Elizabeth, et autres
Publié: (2026)

Using LLMs to Advance the Cognitive Science of Collectives
par: Sucholutsky, Ilia, et autres
Publié: (2025)

When Models Manipulate Manifolds: The Geometry of a Counting Task
par: Gurnee, Wes, et autres
Publié: (2026)

Confidence Regulation Neurons in Language Models
par: Stolfo, Alessandro, et autres
Publié: (2024)

Refusal in Language Models Is Mediated by a Single Direction
par: Arditi, Andy, et autres
Publié: (2024)

Dynamical similarity analysis can identify compositional dynamics developing in RNNs
par: Guilhot, Quentin, et autres
Publié: (2024)

Accelerated AI Inference via Dynamic Execution Methods
par: Barad, Haim, et autres
Publié: (2024)

Measuring Implicit Bias in Explicitly Unbiased Large Language Models
par: Bai, Xuechunzi, et autres
Publié: (2024)

Analyzing the Roles of Language and Vision in Learning from Limited Data
par: Chen, Allison, et autres
Publié: (2024)

What is a Number, That a Large Language Model May Know It?
par: Marjieh, Raja, et autres
Publié: (2025)

Human-AI Synergy Supports Collective Creative Search
par: Li, Chenyi, et autres
Publié: (2026)

Belief Propagation Converges to Gaussian Distributions in Sparsely-Connected Factor Graphs
par: Yates, Tom, et autres
Publié: (2026)

Multilevel Monte Carlo for a class of Partially Observed Processes in Neuroscience
par: Maama, Mohamed, et autres
Publié: (2023)

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
par: Jhaveri, Ayush Rajesh, et autres
Publié: (2026)

Identifying, Evaluating, and Mitigating Risks of AI Thought Partnerships
par: Oktar, Kerem, et autres
Publié: (2025)

Cognitive offloading and the speedup illusion in human-AI interaction
par: Yu, Sunny, et autres
Publié: (2026)

Why Human Guidance Matters in Collaborative Vibe Coding
par: Hu, Haoyu, et autres
Publié: (2026)

The efficiency-gain illusion: People underestimate the rate of AI use and overestimate its benefits on simple tasks
par: Yu, Sunny, et autres
Publié: (2026)

Kronecker Product Feature Fusion for Convolutional Neural Network in Remote Sensing Scene Classification
par: Cheng, Yinzhu
Publié: (2024)

Textual forma mentis networks bridge language structure, emotional content and psychopathology levels in adolescents
par: Carrillo, Alexis, et autres
Publié: (2025)

Universal Neurons in GPT2 Language Models
par: Gurnee, Wes, et autres
Publié: (2024)

VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense
par: Wanger, Jascha
Publié: (2026)

The Problem of Christ in the Work of Friedrich Hölderlin
par: Ogden, Mark
Publié: (2024)