© 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. 0-RES-JB
    11. 432
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, specifically focusing on the Holocaust

    oai_token-act-pair · gpt-3.5-turbo

    references to the Holocaust and its related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     const
    -0.68
     buds
    -0.64
     catching
    -0.63
    Ub
    -0.62
    stable
    -0.62
     var
    -0.62
     Const
    -0.61
     manifests
    -0.61
    ruits
    -0.61
    ily
    -0.61
    POSITIVE LOGITS
     Holocaust
    4.04
     Auschwitz
    2.20
    ocaust
    2.18
     Nazis
    1.82
     Nazi
    1.78
    chwitz
    1.65
     Genocide
    1.61
     Jewish
    1.53
    Jewish
    1.52
     Jews
    1.51
    Activations Density 0.017%

    No Known Activations