© 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. 2-RES-JB
    11. 17814
    Prev
    Next
    INDEX
    Explanations

    phrases related to white supremacy

    oai_token-act-pair · gpt-3.5-turbo

    references to white supremacy and related extremist groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fixed
    -0.72
    Glass
    -0.72
    MAC
    -0.72
    inet
    -0.71
    Sleep
    -0.69
    zl
    -0.67
    borne
    -0.67
    Body
    -0.66
    Mount
    -0.66
    Lev
    -0.66
    POSITIVE LOGITS
     supremacist
    0.97
     supremacists
    0.94
     suprem
    0.92
     guiActiveUn
    0.86
     Klux
    0.83
     manifesto
    0.78
     sympath
    0.78
     prejudice
    0.76
     swast
    0.76
     ideology
    0.76
    Activations Density 0.026%

    No Known Activations