Cover Image

Opening the AI black box: program synthesis via mechanistic interpretability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Michaud, Eric J., Liao, Isaac, Lad, Vedang, Liu, Ziming, Mudide, Anish, Loughridge, Chloe, Guo, Zifan Carl, Kheirkhah, Tara Rezaei, Vukelić, Mateja, Tegmark, Max
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Dictionary Learning with Switch Sparse Autoencoders
by: Mudide, Anish, et al.
Published: (2024)

The Remarkable Robustness of LLMs: Stages of Inference?
by: Lad, Vedang, et al.
Published: (2024)

Opening the black box of language acquisition
by: Michaud, Jérôme, et al.
Published: (2024)

Survival of the Fittest Representation: A Case Study with Modular Addition
by: Ding, Xiaoman Delores, et al.
Published: (2024)

DafnyBench: A Benchmark for Formal Software Verification
by: Loughridge, Chloe, et al.
Published: (2024)

The Quantization Model of Neural Scaling
by: Michaud, Eric J., et al.
Published: (2023)

A Neural Scaling Law from Lottery Ticket Ensembling
by: Liu, Ziming, et al.
Published: (2023)

Physics of Skill Learning
by: Liu, Ziming, et al.
Published: (2025)

OptPDE: Discovering Novel Integrable Systems via AI-Human Collaboration
by: Kantamneni, Subhash, et al.
Published: (2024)

How Do Transformers "Do" Physics? Investigating the Simple Harmonic Oscillator
by: Kantamneni, Subhash, et al.
Published: (2024)

Do Two AI Scientists Agree?
by: Fu, Xinghong, et al.
Published: (2025)

Not All Language Model Features Are One-Dimensionally Linear
by: Engels, Joshua, et al.
Published: (2024)

Universal Neurons in GPT2 Language Models
by: Gurnee, Wes, et al.
Published: (2024)

On the creation of narrow AI: hierarchy and nonlocality of neural network skills
by: Michaud, Eric J., et al.
Published: (2025)

GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective Theory
by: Baek, David D., et al.
Published: (2024)

A Resource Model For Neural Scaling Law
by: Song, Jinyeop, et al.
Published: (2024)

Neural Thermodynamic Laws for Large Language Model Training
by: Liu, Ziming, et al.
Published: (2025)

dafny-annotator: AI-Assisted Verification of Dafny Programs
by: Poesia, Gabriel, et al.
Published: (2024)

Library and Information Science Education in Morocco: Observations on a Recent Visit to the "Ecole des Sciences de l'Information" and the "Centre National de Documentation" in Rabat.
by: Loughridge, B.
Published: (1987)

Harmonic Loss Trains Interpretable AI Models
by: Baek, David D., et al.
Published: (2025)

A benchmark for vericoding: formally verified program synthesis
by: Bursuc, Sergiu, et al.
Published: (2025)

KAN 2.0: Kolmogorov-Arnold Networks Meet Science
by: Liu, Ziming, et al.
Published: (2024)

Language Models Use Trigonometry to Do Addition
by: Kantamneni, Subhash, et al.
Published: (2025)

The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
by: Marks, Samuel, et al.
Published: (2023)

Language Models Represent Space and Time
by: Gurnee, Wes, et al.
Published: (2023)

Towards Understanding Distilled Reasoning Models: A Representational Approach
by: Baek, David D., et al.
Published: (2025)

The Geometry of Concepts: Sparse Autoencoder Feature Structure
by: Li, Yuxiao, et al.
Published: (2024)

Surrogate modeling for interpreting black-box LLMs in medical predictions
by: Han, Changho, et al.
Published: (2026)

Studying and measuring the amount of detergents in sea-water samples in order to eliminate with adsorbents and inorganic nano-adsorbents for the sake of securing the water for marine nourishment pools
by: Kheirkhah, Laya
Published: (2010)

Opening the black box: New insights into the role of temperature in the marine distributions of Pacific salmon
by: Joseph A. Langan, et al.
Published: (2024)

Opening the black box of recurrence in innovation policy. Sources of the Matthew effect in the Argentinean case
by: Diana Suarez
Published: (2021)

Opening the “black box”: Organizational differences between charter schools and traditional public schools
by: Xin Wei
Published: (2014)

An introduction to graphical tensor notation for mechanistic interpretability
by: Taylor, Jordan K.
Published: (2024)

Causal interpretations can be based on mechanistic knowledge
by: James B. Grace, et al.
Published: (2025)

Quantum circuit simulation of black hole evaporation and Maxwell demon interpretation
by: Hadi, H., et al.
Published: (2025)

Opening Pandora's box of transport phenomena
by: Timo Vesala
Published: (2024)

Low-Rank Adapting Models for Sparse Autoencoders
by: Chen, Matthew, et al.
Published: (2025)

Decomposing The Dark Matter of Sparse Autoencoders
by: Engels, Joshua, et al.
Published: (2024)

A mechanistically interpretable neural network for regulatory genomics
by: Tseng, Alex M., et al.
Published: (2024)

Bilinear MLPs enable weight-based mechanistic interpretability
by: Pearce, Michael T., et al.
Published: (2024)