© 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. 0-RES-JB
    11. 10180
    Prev
    Next
    INDEX
    Explanations

    phrases related to marginalized groups, with a focus on the term "minorities."

    oai_token-act-pair · gpt-3.5-turbo

    references to social or ethnic minority groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axe
    -0.67
    cap
    -0.66
    ster
    -0.65
    rive
    -0.64
     Keeper
    -0.63
    stone
    -0.63
     Died
    -0.62
     Pry
    -0.61
    opus
    -0.61
    ear
    -0.61
    POSITIVE LOGITS
     minorities
    3.68
     minority
    1.94
     Hispanics
    1.75
     blacks
    1.69
     Latinos
    1.52
     gays
    1.49
     majorities
    1.45
     Asians
    1.45
     homosexuals
    1.44
     independents
    1.33
    Activations Density 0.019%

    No Known Activations