© 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. 8-RES-JB
    11. 2646
    Prev
    Next
    INDEX
    Explanations

    references to Nazi-related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nazi regime and its associated historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pole
    -0.78
    tis
    -0.74
    Interstitial
    -0.74
    pring
    -0.73
    20439
    -0.72
    Dub
    -0.72
    notes
    -0.71
    player
    -0.68
    area
    -0.67
    forward
    -0.67
    POSITIVE LOGITS
     Hitler
    0.98
    ocaust
    0.88
     Germany
    0.87
    chwitz
    0.86
     Youth
    0.85
     salute
    0.84
     Holocaust
    0.84
    wald
    0.80
     swast
    0.79
     Nazi
    0.79
    Activations Density 0.058%

    No Known Activations