© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1142
    Prev
    Next
    INDEX
    Explanations

    proper names related to various individuals named Karen

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Karen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cision
    -0.69
    apore
    -0.64
    Sax
    -0.61
    ered
    -0.61
    urers
    -0.61
    naires
    -0.61
     Logged
    -0.61
    erie
    -0.61
    xon
    -0.60
    things
    -0.60
    POSITIVE LOGITS
    aii
    0.91
    pillar
    0.83
    ding
    0.78
    fman
    0.74
    atown
    0.73
    ite
    0.71
    verning
    0.71
    lock
    0.70
    lington
    0.69
    NING
    0.69
    Activations Density 0.054%

    No Known Activations