© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3348
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "caused" followed by significant events or consequences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    odan
    -0.78
    �
    -0.74
    ANA
    -0.70
    prints
    -0.67
    antes
    -0.66
    enda
    -0.66
    ヴァ
    -0.66
    ++++++++++++++++
    -0.65
    MENT
    -0.65
    weights
    -0.64
    POSITIVE LOGITS
     succession
    0.81
     resent
    0.71
     bottleneck
    0.70
     downfall
    0.68
     wars
    0.67
     decline
    0.67
     disconnect
    0.67
     Recall
    0.66
     refugee
    0.65
     shortage
    0.63
    Activations Density 0.096%

    No Known Activations