© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11842
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "jihad" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jihad and jihadists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bott
    -0.80
     Lilly
    -0.74
     Cran
    -0.72
    eca
    -0.72
     Ballard
    -0.69
     CG
    -0.69
     Plant
    -0.67
     Dealer
    -0.67
     Cly
    -0.67
     MG
    -0.67
    POSITIVE LOGITS
     jihad
    3.51
     Jihad
    3.18
     jihadists
    2.80
     jihadist
    2.71
     Islamists
    1.93
     caliphate
    1.90
     Islamist
    1.82
    ihadi
    1.75
    ihad
    1.68
    Muslims
    1.64
    Activations Density 0.021%

    No Known Activations