© 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. 11-RES-JB
    11. 6198
    Prev
    Next
    INDEX
    Explanations

    text related to scandals or controversies involving priests and child abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to child abuse, particularly in relation to the Catholic Church and associated figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.92
    ascript
    -0.81
    Haw
    -0.81
    Market
    -0.81
    ebus
    -0.77
     Econom
    -0.77
    NetMessage
    -0.76
    imeter
    -0.73
    haw
    -0.72
     Arrows
    -0.71
    POSITIVE LOGITS
     pedoph
    1.94
     paed
    1.67
     abusers
    1.63
     abuser
    1.51
     mol
    1.47
     abuse
    1.45
     abused
    1.42
    abuse
    1.40
     sexually
    1.37
     child
    1.32
    Activations Density 0.398%

    No Known Activations