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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15101
    Prev
    Next
    INDEX
    Explanations

    terms related to terrorism and extremist groups

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jihadism and extremist groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ðĿ
    -0.92
    rated
    -0.83
    perm
    -0.78
    theless
    -0.77
     DRAG
    -0.75
    ered
    -0.75
    orbit
    -0.74
    eries
    -0.71
    ð
    -0.71
    CAST
    -0.69
    POSITIVE LOGITS
    ihadi
    0.96
     jihadist
    0.94
     jihadists
    0.94
     Islamist
    0.88
     jihad
    0.87
     terrorists
    0.86
     militant
    0.85
     gunmen
    0.85
     extremists
    0.85
     terrorist
    0.84
    Activations Density 0.009%

    No Known Activations