© 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 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. 4-RES-JB
    11. 17003
    Prev
    Next
    INDEX
    Explanations

    references to white supremacist groups such as the Ku Klux Klan (KKK) and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to hate groups, specifically the Ku Klux Klan and related organizations

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

    No Comments

    Negative Logits
    ochond
    -0.78
    RW
    -0.77
    phrine
    -0.77
    Downloadha
    -0.77
    neau
    -0.76
    cially
    -0.73
    */(
    -0.72
    cing
    -0.71
    lessly
    -0.69
    ably
    -0.68
    POSITIVE LOGITS
     Klux
    1.34
     Klan
    1.31
     KKK
    1.06
     affili
    0.77
     robes
    0.77
     supremacist
    0.76
     supremacists
    0.74
     affiliation
    0.74
     NAACP
    0.73
     imperson
    0.72
    Activations Density 0.009%

    No Known Activations