© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20472
    Prev
    Next
    INDEX
    Explanations

    adjectives associated with gender characteristics, particularly masculine and feminine

    oai_token-act-pair · gpt-3.5-turbo

    references to gender roles, specifically masculine and feminine attributes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Assembly
    -0.86
    Deal
    -0.77
    Reviewer
    -0.75
     Tour
    -0.73
    EV
    -0.72
    oulos
    -0.69
    eding
    -0.68
    Reviewed
    -0.68
    EVA
    -0.67
    Publisher
    -0.67
    POSITIVE LOGITS
     masculinity
    1.15
     masculine
    1.14
     feminine
    1.00
     mascul
    0.99
     femin
    0.87
    istries
    0.86
     citiz
    0.83
    femin
    0.82
    WithNo
    0.80
     submar
    0.80
    Activations Density 0.015%

    No Known Activations