Neuron Atlas - Goodfire
Presents an interactive Goodfire tool for exploring language model neurons through overviews, mode landscapes and circuits; the abstract gives no explicit safety motivation.
Research
Goodfire
Understanding and steering neural networks. goodfire.com
Focus All
Topic All
Source Goodfire · 5
Date Past month
2 items
Neurons as an Interpretable Basis
Argues that SwiGLU MLP neurons in language models are sparse, concisely describable, and predictable units of computation, and builds subcircuit and mode analyses plus automated neuron descriptions.
1 item
Shaping and Monitoring Models Through Their Internal Representations
Introduces mechanistic shaping, which trains models through their internal representations to be right for the right reasons, reducing sycophancy, reward hacking and confounder use, and studies effects on monitorability.
1 item
Neural Networks Are Already Clean
Argues that polysemanticity and superposition were misread as arbitrary packing, that networks' own neurons and circuits are legible, and that mechanistic interpretability is more tractable than feared.
1 item
Accelerating Interpretability: A Human Genome Project for AI
Goodfire essay proposing a cross-industry "Human Genome Project for AI" to reverse-engineer frontier LLMs, using agentic experiment-running to scale interpretability research for understanding and aligning AI.