© 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. 11-RES-JB
    11. 9932
    Prev
    Next
    INDEX
    Explanations

    mentions of the Islamic State terrorist group

    oai_token-act-pair · gpt-3.5-turbo

    references to the Islamic State

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemImage
    -0.79
    drops
    -0.78
    milo
    -0.77
    table
    -0.75
    lain
    -0.74
    butt
    -0.71
    aign
    -0.70
    erick
    -0.68
    Scot
    -0.67
    ball
    -0.67
    POSITIVE LOGITS
     State
    1.18
     extremists
    1.09
     Jihad
    1.08
     extremist
    1.04
     supremacists
    1.03
     extremism
    1.01
     militants
    0.99
     fundamentalist
    0.98
     radicals
    0.97
     Emir
    0.95
    Activations Density 0.034%

    No Known Activations