Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8431
    Prev
    Next
    INDEX
    Explanations

    mentions of terrorist organizations like the Islamic State and Al Qaeda

    oai_token-act-pair · gpt-3.5-turbo

    affiliations with Islamist militant groups

    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
    ĸļ
    -0.76
    velt
    -0.70
    Priv
    -0.68
    emouth
    -0.68
    verb
    -0.65
    metry
    -0.65
    phies
    -0.62
    osc
    -0.62
    idge
    -0.62
    imity
    -0.62
    POSITIVE LOGITS
     Islamist
    1.40
     extremist
    1.40
     Boko
    1.36
     Islamic
    1.35
     jihadist
    1.34
     militant
    1.33
     Taliban
    1.32
     ISIL
    1.32
     Daesh
    1.31
    Qaeda
    1.30
    Activations Density 0.249%

    No Known Activations