© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14119
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Islamic"

    oai_token-act-pair · gpt-3.5-turbo

    references to Islamic entities or groups

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    drops
    -0.88
    éĹĺ
    -0.86
    bley
    -0.84
    butt
    -0.74
    erick
    -0.72
    ym
    -0.72
    buck
    -0.71
    vable
    -0.68
    bles
    -0.68
    lain
    -0.68
    POSITIVE LOGITS
     extremism
    1.05
     extremist
    1.02
     supremacists
    1.01
     supremacist
    0.99
     extremists
    0.99
     Jihad
    0.97
     fundamentalist
    0.94
     Brotherhood
    0.93
     Sharia
    0.93
     militant
    0.92
    Activations Density 0.019%

    No Known Activations