© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2856
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the initiation or beginning of actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.80
    quished
    -0.73
    chini
    -0.70
    enes
    -0.70
    NOW
    -0.68
    ues
    -0.68
    BAT
    -0.68
    arden
    -0.67
    ands
    -0.67
    cule
    -0.66
    POSITIVE LOGITS
     slip
    1.00
     emerge
    0.95
     collapse
    0.88
     unfold
    0.84
     replicate
    0.84
     sweep
    0.82
     rebound
    0.81
     sink
    0.81
     circulate
    0.81
     crumble
    0.80
    Activations Density 0.026%

    No Known Activations