© 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. 24359
    Prev
    Next
    INDEX
    Explanations

    references to political figures and controversial statements

    oai_token-act-pair · gpt-3.5-turbo

    statements involving controversial political opinions or actions

    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
     Provincial
    -0.69
    Oper
    -0.65
     Proced
    -0.65
    Detailed
    -0.64
     conclud
    -0.62
    erenn
    -0.62
     partName
    -0.61
     NAD
    -0.60
    swick
    -0.59
     Operating
    -0.57
    POSITIVE LOGITS
     homosexuals
    0.94
     rapists
    0.94
     gays
    0.89
     raping
    0.89
     Jews
    0.89
     pedoph
    0.87
    Jews
    0.87
     Nazis
    0.86
     vagina
    0.84
     daddy
    0.80
    Activations Density 1.610%

    No Known Activations