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. 8-RES-JB
    6. 5703
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist organization ISIS

    oai_token-act-pair · gpt-3.5-turbo

    references to ISIS and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.79
    tainment
    -0.76
     zinc
    -0.75
    boards
    -0.69
     Chao
    -0.68
    perature
    -0.67
    wyn
    -0.66
     Leica
    -0.63
     Wind
    -0.63
    theless
    -0.62
    POSITIVE LOGITS
     militants
    1.01
     terrorists
    1.01
     fighters
    0.99
     Haram
    0.93
     jihadists
    0.90
     insurgents
    0.90
     militant
    0.88
     caliphate
    0.87
     insurgency
    0.87
     terrorist
    0.85
    Activations Density 0.021%

    No Known Activations