© 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. 10-RES-JB
    11. 13688
    Prev
    Next
    INDEX
    Explanations

    references to Jewish culture, organizations, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to Jewish identity and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mson
    -0.76
    Nap
    -0.75
    aldo
    -0.71
    xon
    -0.71
    ttes
    -0.70
     Rasmussen
    -0.70
    doors
    -0.69
     Archdemon
    -0.68
    )=(
    -0.68
    tnc
    -0.68
    POSITIVE LOGITS
     Israelis
    0.95
     settlers
    0.94
     communal
    0.93
     supremacist
    0.88
     Sabbath
    0.87
     settlements
    0.87
     rabb
    0.87
     Settlement
    0.82
     Federation
    0.82
     supremacists
    0.80
    Activations Density 0.041%

    No Known Activations