© 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. 9-RES-JB
    11. 14744
    Prev
    Next
    INDEX
    Explanations

    references to gender-related beliefs and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gender stereotypes and beliefs about women's roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Gender Features

    No Comments

    Negative Logits
     sqor
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
     misunder
    -0.66
     partName
    -0.64
    enture
    -0.63
     Printed
    -0.62
    ktop
    -0.62
    iasm
    -0.60
     aback
    -0.58
    Marginal
    -0.58
    POSITIVE LOGITS
     homosexuals
    0.91
     raping
    0.83
     gays
    0.82
     homosexuality
    0.81
     raped
    0.80
     rapists
    0.79
    Jews
    0.77
     adultery
    0.75
     Nazis
    0.72
     Jews
    0.72
    Activations Density 1.050%

    No Known Activations