Jun 3, 2024
RNNs represent belief state geometry in hidden state
Keenan Pepper
Details
Details



Summary
The Shai et al. experiments on transformers (finding belief state geometry in the residual stream) have been replicated in RNNs with the hidden state instead of the residual stream. In general the belief state is stored linearly, but not in any particular layer, rather spread out across layers.
Cite this work:
@misc {
title={
RNNs represent belief state geometry in hidden state
},
author={
Keenan Pepper
},
date={
6/3/24
},
organization={Apart Research},
note={Research submission to the research sprint hosted by Apart.},
howpublished={https://apartresearch.com}
}
Review
Review



Reviewer's Comments
Reviewer's Comments



No reviews are available yet
Feb 20, 2025
Deception Detection Hackathon: Preventing AI deception
Read More
Mar 18, 2025
Safe ai
The rapid adoption of AI in critical industries like healthcare and legal services has highlighted the urgent need for robust risk mitigation mechanisms. While domain-specific AI agents offer efficiency, they often lack transparency and accountability, raising concerns about safety, reliability, and compliance. The stakes are high, as AI failures in these sectors can lead to catastrophic outcomes, including loss of life, legal repercussions, and significant financial and reputational damage. Current solutions, such as regulatory frameworks and quality assurance protocols, provide only partial protection against the multifaceted risks associated with AI deployment. This situation underscores the necessity for an innovative approach that combines comprehensive risk assessment with financial safeguards to ensure the responsible and secure implementation of AI technologies across high-stakes industries.
Read More
Mar 18, 2025
Cite2Root
Regain information autonomy by bringing people closer to the source of truth.
Read More
Feb 20, 2025
Deception Detection Hackathon: Preventing AI deception
Read More
Mar 18, 2025
Safe ai
The rapid adoption of AI in critical industries like healthcare and legal services has highlighted the urgent need for robust risk mitigation mechanisms. While domain-specific AI agents offer efficiency, they often lack transparency and accountability, raising concerns about safety, reliability, and compliance. The stakes are high, as AI failures in these sectors can lead to catastrophic outcomes, including loss of life, legal repercussions, and significant financial and reputational damage. Current solutions, such as regulatory frameworks and quality assurance protocols, provide only partial protection against the multifaceted risks associated with AI deployment. This situation underscores the necessity for an innovative approach that combines comprehensive risk assessment with financial safeguards to ensure the responsible and secure implementation of AI technologies across high-stakes industries.
Read More
Feb 20, 2025
Deception Detection Hackathon: Preventing AI deception
Read More
Mar 18, 2025
Safe ai
The rapid adoption of AI in critical industries like healthcare and legal services has highlighted the urgent need for robust risk mitigation mechanisms. While domain-specific AI agents offer efficiency, they often lack transparency and accountability, raising concerns about safety, reliability, and compliance. The stakes are high, as AI failures in these sectors can lead to catastrophic outcomes, including loss of life, legal repercussions, and significant financial and reputational damage. Current solutions, such as regulatory frameworks and quality assurance protocols, provide only partial protection against the multifaceted risks associated with AI deployment. This situation underscores the necessity for an innovative approach that combines comprehensive risk assessment with financial safeguards to ensure the responsible and secure implementation of AI technologies across high-stakes industries.
Read More
Feb 20, 2025
Deception Detection Hackathon: Preventing AI deception
Read More
Mar 18, 2025
Safe ai
The rapid adoption of AI in critical industries like healthcare and legal services has highlighted the urgent need for robust risk mitigation mechanisms. While domain-specific AI agents offer efficiency, they often lack transparency and accountability, raising concerns about safety, reliability, and compliance. The stakes are high, as AI failures in these sectors can lead to catastrophic outcomes, including loss of life, legal repercussions, and significant financial and reputational damage. Current solutions, such as regulatory frameworks and quality assurance protocols, provide only partial protection against the multifaceted risks associated with AI deployment. This situation underscores the necessity for an innovative approach that combines comprehensive risk assessment with financial safeguards to ensure the responsible and secure implementation of AI technologies across high-stakes industries.
Read More

Sign up to stay updated on the
latest news, research, and events

Sign up to stay updated on the
latest news, research, and events

Sign up to stay updated on the
latest news, research, and events

Sign up to stay updated on the
latest news, research, and events