Goodfire researcher claims neural nets are more interpretable than thought
Stanford's Chris Potts calls the 26,000-word post a hunch that does not make interpretability easier.
1
Stories per day · 30 days
2 RSS
Relatedmechanistic-interpretability3goodfire2inceptionv12qwen32ai-safety1neural-networks1polysemanticity1sparse-autoencoders1
4 stories, newest first · one card per story
Stories tagged #superposition
Is AI interpretability close to a breakthrough? A new essay has researchers divided
Nick Cammarata argues famous polysemantic neurons were misread, claiming most Qwen3-32B neurons have one job.
7
Neural Networks Are Already Clean
A Goodfire researcher argues neural networks are already interpretable and superposition was misread.
12
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
Transformers superpose next-token distributions from mixed text streams, and fine-tuning can restore that linearity.