Unverified50% confidenceFactExact time
Anthropic 发布了《Transformer Circuits》系列文章
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe field of mechanistic interpretability was largely founded by the Anthropic research team (especially Chris Olah) around 2021 through the "Transformer Circuits" series of papers.69% similarUnverified线性注意力思路由 Katharopoulos 等人在 2020 年论文《Transformers are RNNs》中系统化63% similarUnverifiedTransformer原始论文于2017年由Google Brain团队发表60% similarVerifiedTransformer最初由Vaswani等人在2017年的论文《Attention Is All You Need》中提出，用于机器翻译任务56% similarUnverified归纳头（induction heads）是 Anthropic 团队于2022年发现的电路案例，由两个注意力头协作完成上文信息复制55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/809964API
curl https://kongchang.com/api/v1/knowledge/claims/809964MCP
get_claim(id=809964)