Nick Cammarata：万亿参数模型中绝大多数神经元已可解读
Highly recommended read. This is the type of interpretability work that we need more of. "We can n...
前 OpenAI 研究者说万亿参数模型里大部分神经元都能解读了，早期只有 2%，观点转变很值得看。
前 OpenAI 早期可解释性研究者 Nick Cammarata 发文称，早期只有约 2% 的神经元能用原始工具解读清楚，因此他曾对机制可解释性持悲观态度。借助现代 agentic 工具，模型中绝大多数神经元已可解读，覆盖参数规模达到万亿级别。许多此前被认为是“纠缠神经元”的著名案例实为误解。他认为机制可解释性问题可能很快就能解决，并称这可能印证了“简单方法配合超大规模已经有效”的 bitter lesson。
Highly recommended read. This is the type of interpretability work that we need more of. "We can n...
Highly recommended read. This is the type of interpretability work that we need more of. "We can now understand most neurons in models up to trillions of parameters, and think the outlook for mechanistic interpretability may be far better than we thought." Nick @nickcammarata interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works already-clean.goodfire.com 🔗 View Quoted Tweet 💬 7 🔄 6 ❤️ 17 👀 1749 📊 9 ⚡
