© 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. 8-RES-JB
    11. 1125
    Prev
    Next
    INDEX
    Explanations

    instances of the word "jihad" or its derivatives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jihad and jihadist activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Veter
    -0.72
    arest
    -0.65
     Pony
    -0.62
     Ambro
    -0.62
     Dull
    -0.61
     Scotch
    -0.61
    Board
    -0.61
     Quadro
    -0.61
    bye
    -0.59
     Leica
    -0.59
    POSITIVE LOGITS
    ihad
    1.10
     jihad
    1.07
    istan
    1.04
    zai
    1.01
    ihadi
    0.97
    istani
    0.95
    aeda
    0.89
     fighters
    0.88
    uddin
    0.87
    iyah
    0.87
    Activations Density 0.022%

    No Known Activations