Product
GPT-4 can now explain what every neuron in GPT-2 is doing
OpenAI Blog · Jul 18, 2026 · 2 min read
Here's a problem that has kept AI researchers up at night: you build a massive language model, it works brilliantly, bu...
Topic: mechanistic-interpretability
3 articles
Explore our coverage of mechanistic-interpretability — 3 curated articles, summaries, and related resources from the Inblix archive.
Research
Anthropic’s Claude hides its reasoning in a secret ‘J-space’
MIT Technology Review · Jul 13, 2026 · 3 min read
Anthropic’s latest dive into mechanistic interpretability has surfaced something genuinely weird: a hidden conceptual s...
Product
Anthropic bets on sparser, simpler neural nets you can actually read
OpenAI Blog · Jul 12, 2026 · 3 min read
For years, the playbook for understanding what a neural network is actually doing has been brutally consistent: take a...