© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6868
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating gender

    oai_token-act-pair · gpt-3.5-turbo
    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
     FINAL
    -0.69
     Background
    -0.63
    perture
    -0.60
    OVER
    -0.60
    IOR
    -0.59
     TOTAL
    -0.58
    IRE
    -0.58
     interchange
    -0.58
    antage
    -0.56
     prelim
    -0.55
    POSITIVE LOGITS
    she
    0.83
    leans
    0.79
    acle
    0.76
    nery
    0.73
     herself
    0.70
    girlfriend
    0.66
    acles
    0.63
     she
    0.63
    esses
    0.63
    urga
    0.63
    Activations Density 0.048%

    No Known Activations