Topics
Results for “interpretability”
12 results
- Tools for exploring the souls of large language models — Hacker News · Seen · 52 points
- Building Auditable AI Text Detectors with Sparse Autoencoders — Hugging Face Papers · Seen · 13 points
- Mixture of Wide Experts: Sparse Routing for Interpretable Native Coordinates — arXiv AI Papers · Seen
- Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights — 2 sources · Seen · 2,935 points
- From Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs — arXiv AI Papers · Seen
- Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation Data — arXiv AI Papers · Seen
- Qwen has alter egos triggered by flipping a single neuron — Hacker News · Seen · 52 points
- When Planning Problems Become Hard for LLMs: Separating Structural Complexity from Semantic Interpretability — arXiv AI Papers · Seen
- NVIDIA Kumo Forecast Combines Pretrained Time-Series Representations with Historical Pattern Retrieval and Interpretability — Hugging Face Blog · Seen
- AI torture chamber: deep dive into whether model can feel pain — DEV Community · Seen
- Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability — arXiv AI Papers · Seen
- How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings — arXiv AI Papers · Seen