© 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. 12-RES-JB
    11. 3064
    Prev
    Next
    INDEX
    Explanations

    words related to specific events, locations, and organizations surrounding a white nationalist rally

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms and phrases related to white nationalist and supremacist movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    20439
    -0.86
    neau
    -0.84
    tis
    -0.82
    lessly
    -0.77
    ysis
    -0.72
    balanced
    -0.71
    thumbnails
    -0.69
    independent
    -0.69
    poor
    -0.68
    =~
    -0.66
    POSITIVE LOGITS
     Klan
    1.01
     salute
    0.96
     rally
    0.95
     rallies
    0.93
     Klux
    0.90
     sympath
    0.89
     KKK
    0.88
     thugs
    0.85
     marches
    0.84
     supremacist
    0.83
    Activations Density 0.145%

    No Known Activations