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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9599
    Prev
    Next
    INDEX
    Explanations

    the keyword "Israel"

    oai_token-act-pair · gpt-3.5-turbo

    references to Israel and its historical and political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mson
    -0.76
    ĸļ
    -0.72
    luaj
    -0.72
    nant
    -0.72
    apple
    -0.71
    geoning
    -0.71
    ttes
    -0.71
    utic
    -0.69
    iddler
    -0.68
     Jackets
    -0.68
    POSITIVE LOGITS
     Aviv
    0.90
    anyahu
    0.88
    ites
    0.85
    apolis
    0.79
    aretz
    0.78
    Israel
    0.77
    ifa
    0.74
     Israel
    0.73
     Netanyahu
    0.71
     Juda
    0.70
    Activations Density 0.028%

    No Known Activations