Copertina

Challenges in Mechanistically Interpreting Model Representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Golechha, Satvik, Dao, James
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Progress Measures for Grokking on Real-world Tasks
di: Golechha, Satvik
Pubblicazione: (2024)

Training Neural Networks for Modularity aids Interpretability
di: Golechha, Satvik, et al.
Pubblicazione: (2024)

Among Us: A Sandbox for Measuring and Detecting Agentic Deception
di: Golechha, Satvik, et al.
Pubblicazione: (2025)

NICE: To Optimize In-Context Examples or Not?
di: Srivastava, Pragya, et al.
Pubblicazione: (2024)

Building Better Deception Probes Using Targeted Instruction Pairs
di: Natarajan, Vikram, et al.
Pubblicazione: (2026)

Studying Cross-cluster Modularity in Neural Networks
di: Golechha, Satvik, et al.
Pubblicazione: (2025)

ABBEL: LLM Agents Acting through Belief Bottlenecks Expressed in Language
di: Lidayan, Aly, et al.
Pubblicazione: (2025)

Who's the Evil Twin? Differential Auditing for Undesired Behavior
di: Balappanawar, Ishwar, et al.
Pubblicazione: (2025)

Logic Sketch Prompting (LSP): A Deterministic and Interpretable Prompting Method
di: Tripathi, Satvik
Pubblicazione: (2025)

Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
di: Maghsoudi, Maryam, et al.
Pubblicazione: (2026)

reward-lens: A Mechanistic Interpretability Library for Reward Models
di: Nadaf, Mohammed Suhail B
Pubblicazione: (2026)

A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models
di: Lin, Zihao, et al.
Pubblicazione: (2025)

MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
di: He, Jesse, et al.
Pubblicazione: (2026)

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
di: Winninger, Thomas, et al.
Pubblicazione: (2025)

nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers
di: Dumas, Clément
Pubblicazione: (2025)

Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
di: Yan, Ge, et al.
Pubblicazione: (2025)

Mechanistic Interpretability for Transformer-based Time Series Classification
di: Kalnāre, Matīss, et al.
Pubblicazione: (2025)

Mechanistic Interpretability of GPT-like Models on Summarization Tasks
di: Mishra, Anurag
Pubblicazione: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
di: Cho, Hakaze, et al.
Pubblicazione: (2025)

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications
di: Lee, Yoon Pyo
Pubblicazione: (2025)

Towards Mechanistic Interpretability of Graph Transformers via Attention Graphs
di: El, Batu, et al.
Pubblicazione: (2025)

MIB: A Mechanistic Interpretability Benchmark
di: Mueller, Aaron, et al.
Pubblicazione: (2025)

Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
di: Yıldırım, Alper
Pubblicazione: (2026)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
di: Kim, Geonhee, et al.
Pubblicazione: (2024)

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability
di: Zhang, Shichang, et al.
Pubblicazione: (2025)

Mechanistic Interpretability with Sparse Autoencoder Neural Operators
di: Tolooshams, Bahareh, et al.
Pubblicazione: (2025)

The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis
di: Mueller, Aaron, et al.
Pubblicazione: (2024)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
di: Wang, Xu, et al.
Pubblicazione: (2026)

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
di: Simbeck, Katharina, et al.
Pubblicazione: (2025)

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
di: Sun, Jiuding, et al.
Pubblicazione: (2025)

Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
di: Méloux, Maxime, et al.
Pubblicazione: (2025)

Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
di: Méloux, Maxime, et al.
Pubblicazione: (2025)

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima
di: Tang, Yiming, et al.
Pubblicazione: (2025)

TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research
di: Harrasse, Abir, et al.
Pubblicazione: (2025)

Mamba: Linear-Time Sequence Modeling with Selective State Spaces
di: Gu, Albert, et al.
Pubblicazione: (2023)

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs
di: Song, Xiangchen, et al.
Pubblicazione: (2025)

Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching
di: Bahador, Nooshin
Pubblicazione: (2025)

Interpretable Representation Learning for Additive Rule Ensembles
di: Behzadimanesh, Shahrzad, et al.
Pubblicazione: (2025)

MemER: Scaling Up Memory for Robot Control via Experience Retrieval
di: Sridhar, Ajay, et al.
Pubblicazione: (2025)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
di: Chen, Jianhui, et al.
Pubblicazione: (2026)