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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 6913
    Prev
    Next
    INDEX
    Explanations

    mentions of militant groups and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to militant and insurgent groups

    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
     cones
    -0.73
    iture
    -0.71
    olor
    -0.71
     impressions
    -0.70
    bugs
    -0.69
    ¢
    -0.69
     Guests
    -0.69
    Elsa
    -0.69
    airs
    -0.69
    ices
    -0.68
    POSITIVE LOGITS
     militant
    3.27
     extremist
    1.88
     separatist
    1.72
     insurgent
    1.71
     jihadist
    1.60
     milit
    1.57
     radical
    1.54
    radical
    1.45
     terrorist
    1.42
     fundamentalist
    1.41
    Activations Density 0.010%

    No Known Activations