© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 17127
    Prev
    Next
    INDEX
    Explanations

    references to white supremacy and neo-Nazis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to white supremacist and neo-Nazi groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysis
    -0.78
    neau
    -0.77
    payer
    -0.70
    tis
    -0.70
     Revenue
    -0.70
    borne
    -0.68
    Rate
    -0.65
    cit
    -0.65
     Administ
    -0.64
     Balanced
    -0.64
    POSITIVE LOGITS
     Klan
    0.95
     KKK
    0.90
     Klux
    0.90
     paramilitary
    0.89
     thugs
    0.87
     clown
    0.85
     supremacists
    0.82
     marching
    0.82
    Nazis
    0.82
     swast
    0.81
    Activations Density 0.074%

    No Known Activations