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. 6-RES-JB
    6. 8322
    Prev
    Next
    INDEX
    Explanations

    references to political figures, especially pertaining to Prime Minister Narendra Modi

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures, specifically Narendra Modi

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.79
    oning
    -0.73
    allo
    -0.72
    erie
    -0.72
    hops
    -0.71
    20439
    -0.71
    ubb
    -0.70
     DRAG
    -0.69
    ramid
    -0.68
    inventoryQuantity
    -0.67
    POSITIVE LOGITS
     Modi
    1.13
     Tayyip
    0.98
    lihood
    0.95
     Hussein
    0.94
     Kumar
    0.91
     Narendra
    0.90
     Trudeau
    0.77
     Sark
    0.77
    nam
    0.76
    sson
    0.73
    Activations Density 0.019%

    No Known Activations