Max Tegmark

papers

1,344

total citations

papers (12)

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

NEURIPS 2023arXiv

142

citations

The Quantization Model of Neural Scaling

NEURIPS 2023arXiv

126

citations

Poisson Flow Generative Models

NEURIPS 2022arXiv

109

citations

Not All Language Model Features Are One-Dimensionally Linear

ICLR 2025arXiv

101

citations

Remarkable Robustness of LLMs: Stages of Inference?

NEURIPS 2025arXiv

citations

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

ICML 2025arXiv

citations

Dense SAE Latents Are Features, Not Bugs

NEURIPS 2025arXiv

citations

Scaling Laws For Scalable Oversight

NEURIPS 2025arXiv

citations

On the creation of narrow AI: hierarchy and nonlocality of neural network skills

NEURIPS 2025arXiv

citations

Max Tegmark

papers (12)

Language Models Represent Space and Time

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

Towards Understanding Grokking: An Effective Theory of Representation Learning

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

The Quantization Model of Neural Scaling

Poisson Flow Generative Models

Not All Language Model Features Are One-Dimensionally Linear

Remarkable Robustness of LLMs: Stages of Inference?

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Dense SAE Latents Are Features, Not Bugs

Scaling Laws For Scalable Oversight

On the creation of narrow AI: hierarchy and nonlocality of neural network skills

papers (12)

Language Models Represent Space and Time

AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity

Towards Understanding Grokking: An Effective Theory of Representation Learning

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

The Quantization Model of Neural Scaling

Poisson Flow Generative Models

Not All Language Model Features Are One-Dimensionally Linear

Remarkable Robustness of LLMs: Stages of Inference?

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Dense SAE Latents Are Features, Not Bugs

Scaling Laws For Scalable Oversight

On the creation of narrow AI: hierarchy and nonlocality of neural network skills