© 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. 9-RES-JB
    11. 11738
    Prev
    Next
    INDEX
    Explanations

    mentions of the Nazi regime and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nazi regime and related historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pole
    -0.81
    pring
    -0.77
    tis
    -0.77
    area
    -0.76
    20439
    -0.76
    Dub
    -0.76
    changes
    -0.73
    notes
    -0.72
    Interstitial
    -0.71
    Asia
    -0.69
    POSITIVE LOGITS
     Hitler
    1.04
    ocaust
    1.01
    chwitz
    0.97
     Holocaust
    0.92
     Germany
    0.89
     salute
    0.87
     extermination
    0.87
     Nazi
    0.86
     Adolf
    0.85
    wald
    0.85
    Activations Density 0.082%

    No Known Activations