© 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. 8-RES-JB
    11. 14288
    Prev
    Next
    INDEX
    Explanations

    words related to transgender individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to transgender individuals and issues

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    steen
    -0.82
     Manufacturer
    -0.80
    cv
    -0.70
     reper
    -0.70
     Dying
    -0.68
    rpm
    -0.66
    pload
    -0.66
    akings
    -0.66
    Posts
    -0.65
     Delicious
    -0.64
    POSITIVE LOGITS
    gender
    1.11
     bathroom
    0.94
     restroom
    0.87
    sexual
    0.86
     identities
    0.83
    obic
    0.82
    genic
    0.81
     bathrooms
    0.79
     genital
    0.79
    ethnic
    0.79
    Activations Density 0.022%

    No Known Activations