Concept · 23 episode(s)

Causal Intervention

← all concepts

Definition

Causal interventions in a neural network swap, ablate, or patch internal activations to test whether a particular component causes a behavior, not just correlates with it. They’re the gold standard in mechanistic interpretability for the same reason randomized trials are in medicine: observation can’t distinguish cause from confound.

Episodes covering this

  1. 241
    Swapping the Name Did Nothing, But Hedging Moved Every Model
    It's How You Ask: Gender-Associated Linguistic Bias in LLMs
    Koevering, Field · Data Science and AI Institute·18 min·Aug 14, 2026
  2. 237
    The Model Built a Perfect Map of the Puzzle, Then Lost It
    Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking
    Pereira, Zuidema · Artificial Intelligence Program·19 min·Aug 10, 2026
  3. 235
    Why Chatbot Safety Erodes 350 Messages Into a Real Conversation
    DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots
    Moore, Mock, Mai et al. · Stanford University·18 min·Aug 06, 2026
  4. 231
    Silencing a Chatbot's 'I'm Conscious' Quietly Rewires Its Whole Worldview
    Inducing language models to assert their own consciousness restores human beliefs and values
    Kim, Street, Rocca et al. · Google·18 min·Jul 31, 2026
  5. 229
    One Word Flips a Chatbot From Backbone to Yes-Man
    Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models
    Parikh · Cornell Tech·21 min·Jul 28, 2026
  6. 212
    The Fact Was in the Wrong Drawer: Why Fine-Tuned Models Can't Reason With What They Know
    Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning
    Dai, Rao, Wang et al. · HKUST(GZ)·14 min·Jul 10, 2026
  7. 204
    The Length Estimate Hiding Inside a Word-by-Word Model
    How Much is Left? LLMs Linearly Encode Their Remaining Output Length
    Merzouk, Carpov, Bronzi et al. · Mila·14 min·Jul 07, 2026
  8. 203
    The Thought a Model Doesn't Say — and the Lens That Reads It
    Verbalizable Representations Form a Global Workspace in Language Models
    Gurnee, Sofroniew, Pearce et al. · Anthropic·16 min·Jul 07, 2026
  9. 181
    How to Backpropagate Blame Through a Team of Chatbots — And When It Backfires
    GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems
    Yang, Alrabah, Hakkani-Tür et al. · University of Illinois Urbana-Champaign·20 min·Jun 29, 2026
  10. 174
    When the AI 'Schemes,' It's Usually Just Lazy or Confused
    Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment
    Singh, Kroiz, Rajamanoharan et al. · MATS·28 min·Jun 25, 2026
  11. 172
    One Bad Token Can Sink a Model's Math, And You Can Delete It
    Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning
    Ko, Kang, Lee · Seoul National University·22 min·Jun 25, 2026
  12. 151
    Why More Experience Made This AI Agent Worse, And How to Fix It
    Not All Skills Help: Measuring and Repairing Agent Knowledge
    Wang, Zhou, Liang et al. · UNC Chapel Hill·28 min·Jun 16, 2026
  13. 141
    How Two Tokens Reopened a Reasoning Method the Field Had Given Up On
    Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
    Yang, Chen, Wu et al. · HKUST(GZ)·29 min·Jun 12, 2026
  14. 140
    When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
    Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
    Scalena, Candussio, Bortolussi et al. · University of Groningen / University of Milano-Bicocca·27 min·Jun 12, 2026
  15. 098
    Finding Millions of Readable Concepts Inside a Real, Deployed AI Model
    Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
    Templeton, Conerly, Marcus et al. · Anthropic·28 min·May 29, 2026
  16. 091
    When Better Fine-Tuning Can't Help: A Geometric Impossibility in LLM Causal Reasoning
    Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
    Roy, Parbhoo · SIRE·24 min·May 28, 2026
  17. 086
    Why Frozen-Weight Agents Still Get Worse Over Time
    Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems
    Zhu, Ro, Robertson et al. · The University of Texas at Austin·23 min·May 27, 2026
  18. 055
    Why LLM Judges Flip Their Verdicts When You Change the Question Format
    Judge Circuits
    Feldhus, Baeumel, Golimblevskaia et al. · Technische Universität Berlin / BIFOLD·26 min·May 19, 2026
  19. 042
    An Agentic Scientific Computing System That Actually Remembers What It Learns
    GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms
    Toscano, Chai, Karniadakis · Division of Applied Mathematics·30 min·May 13, 2026
  20. 038
    How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
    How LLMs Are Persuaded: A Few Attention Heads, Rerouted
    Sun, Kong, Zhang et al. · Northeastern University·23 min·May 12, 2026
  21. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
    The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
    Elbadry, Heakl, Zhang et al. · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)·27 min·May 12, 2026
  22. 026
    What RL Actually Does to Language Models, at the Token Level
    Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
    Akgül, Kannan, Neiswanger et al. · University of Southern California·24 min·May 08, 2026
  23. 023
    Why a Small Agent Confidently Overwrites Memories It Doesn't Understand
    What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis
    Mao, Zhao, Penn et al. · City University of Hong Kong·23 min·May 07, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.