© 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. 1-RES-JB
    11. 2723
    Prev
    Next
    INDEX
    Explanations

    mentions of Jewish people or related topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Jewish people or references specifically related to Jews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneously
    -0.74
    SIGN
    -0.72
    shown
    -0.72
    tten
    -0.71
    ctive
    -0.69
    nant
    -0.69
    URRENT
    -0.69
    inventoryQuantity
    -0.68
    tnc
    -0.66
    ateur
    -0.64
    POSITIVE LOGITS
     Jews
    1.10
    geist
    0.92
     Israelis
    0.91
    Jews
    0.87
    Semitism
    0.87
     Juda
    0.86
    ellery
    0.83
    ophobia
    0.82
    eni
    0.80
     rabb
    0.79
    Activations Density 0.009%

    No Known Activations