© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18747
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Jewish."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Jewish community and identity

    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
    aunder
    -0.91
    tesy
    -0.79
    lain
    -0.76
    staking
    -0.74
    orative
    -0.74
     Archdemon
    -0.73
    raints
    -0.73
    nant
    -0.72
    Downloadha
    -0.71
    lay
    -0.70
    POSITIVE LOGITS
     Jewish
    1.08
     Jews
    1.05
     Israelis
    1.03
    Jewish
    0.99
     synagogue
    0.97
    Israeli
    0.96
     rabb
    0.96
     Torah
    0.94
    Semitism
    0.94
     Sabbath
    0.90
    Activations Density 0.010%

    No Known Activations