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. 10-RES-JB
    6. 3643
    Prev
    Next
    INDEX
    Explanations

    phrases related to political unrest or conflict

    oai_token-act-pair · gpt-3.5-turbo

    mentions of violence and clashes, particularly in political or protest contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cary
    -0.87
    maxwell
    -0.76
     Ballard
    -0.71
     NYC
    -0.71
     Wonderland
    -0.69
    natureconservancy
    -0.67
     ADA
    -0.66
     AMERICA
    -0.65
    Utah
    -0.65
    avery
    -0.64
    POSITIVE LOGITS
     besie
    1.02
     Morsi
    0.96
     amid
    0.96
     Syri
    0.92
     Islamists
    0.91
     accusing
    0.89
     Houth
    0.82
     Ankara
    0.81
     denouncing
    0.81
     ousted
    0.81
    Activations Density 0.449%

    No Known Activations