© 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 EvalsExportsAPI 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. 4134
    Prev
    Next
    INDEX
    Explanations

    statements or beliefs related to gender roles and stereotypes

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific beliefs and theories related to gender

    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
    WARE
    -0.81
    dding
    -0.78
    yssey
    -0.77
    media
    -0.75
    enture
    -0.72
    rehensive
    -0.72
    Wra
    -0.70
    DCS
    -0.69
    icion
    -0.68
     aback
    -0.67
    POSITIVE LOGITS
     homosexuality
    0.96
     homosexuals
    0.84
     polygamy
    0.83
     deform
    0.78
     XY
    0.77
     communism
    0.76
     biologically
    0.76
     homosexual
    0.76
     sexes
    0.76
     ______
    0.75
    Activations Density 0.924%

    No Known Activations