Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified50% confidenceFactExact time

机制可解释性领域在很大程度上由 Anthropic 研究团队（尤其是 Chris Olah）在2021年前后通过「Transformer 电路」系列论文奠定基础

1

Sources

50%

Confidence

Long-term

Relevance

7/8/2026

First Seen

Sources

语言模型中的全局工作空间理论：AI可解释性新视角

hackernewshackernews7/6/2026

Related Claims

UnverifiedAnthropic在2023年发表了'表征工程'研究，Turner等人发表了'激活加法'工作，都是该技术范式的代表性成果71% similar Unverified线性注意力思路由 Katharopoulos 等人在 2020 年论文《Transformers are RNNs》中系统化70% similar Unverified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67% similar UnverifiedAnthropic研究团队2023年发表了关于奉承性偏差的系统性分析63% similar UnverifiedAnthropic 的 Chris Olah 是机械可解释性领域的代表人物之一62% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/274096

API

curl https://kongchang.com/api/v1/knowledge/claims/274096

MCP

get_claim(id=274096)