会员服务
Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy
Arxiv
0+阅读 · 2月19日
Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees
Arxiv
0+阅读 · 2月18日
Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic Interpretability
Arxiv
0+阅读 · 2月7日
Disentangling meaning from language in LLM-based machine translation
Arxiv
0+阅读 · 2月4日
Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
Arxiv
0+阅读 · 2月3日
Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models
Arxiv
0+阅读 · 2月3日
On the Theoretical Foundation of Sparse Dictionary Learning in Mechanistic Interpretability
Arxiv
0+阅读 · 1月13日
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Arxiv
0+阅读 · 1月20日
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Arxiv
1+阅读 · 1月26日
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Arxiv
0+阅读 · 1月22日
Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability
Arxiv
0+阅读 · 1月29日
Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models
Arxiv
0+阅读 · 1月14日
Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
Arxiv
0+阅读 · 1月6日
Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
Arxiv
0+阅读 · 1月6日
When the Coffee Feature Activates on Coffins: An Analysis of Feature Extraction and Steering for Mechanistic Interpretability
Arxiv
0+阅读 · 1月6日
参考链接
微信扫码咨询专知VIP会员
Top