© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3549
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination and bias against specific groups or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to discrimination and marginalized groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gency
    -0.78
    forward
    -0.75
    ciation
    -0.72
     Tycoon
    -0.72
    éĹĺ
    -0.70
    fax
    -0.69
    fecture
    -0.68
    dust
    -0.67
     Logged
    -0.67
    osate
    -0.66
    POSITIVE LOGITS
     minorities
    1.67
     marginalized
    1.39
     gays
    1.36
     women
    1.33
     minority
    1.32
     homosexuals
    1.32
     LGBTQ
    1.32
     transgender
    1.28
     Latinos
    1.27
     lesbians
    1.27
    Activations Density 0.235%

    No Known Activations