#mechanistic-understanding News & Analysis

3 articles tagged with #mechanistic-understanding. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AINeutralarXiv – CS AI · 3d ago7/10

🧠

Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN

Researchers reverse-engineered a Sokoban-playing RNN trained with model-free reinforcement learning and discovered that the network encodes planning strategies through specialized neural channels that represent directional movements and learned transition models. The findings demonstrate that neural networks can develop interpretable planning algorithms without explicit supervision, with path channels and extension kernels working together to implement bidirectional search and backtracking.

AINeutralarXiv – CS AI · May 96/10

🧠

HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory

Researchers introduce HyperLens, a high-resolution analysis tool that measures cognitive effort in large language models by tracking confidence trajectories across transformer layers. The study reveals that complex tasks consistently require higher cognitive effort and identifies how standard fine-tuning can paradoxically reduce model performance by decreasing necessary cognitive investment.

AINeutralarXiv – CS AI · Apr 156/10

🧠

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework

Researchers introduce Safe-SAIL, a framework that uses sparse autoencoders to interpret safety features in large language models across four domains (pornography, politics, violence, terror). The work reduces interpretation costs by 55% and identifies 1,758 safety-related features with human-readable explanations, advancing mechanistic understanding of AI safety.