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. 3-RES-JB
    6. 2167
    Prev
    Next
    INDEX
    Explanations

    mentions of "First Nations."

    oai_token-act-pair · gpt-3.5-turbo

    references to indigenous governments and their governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azine
    -0.94
    utic
    -0.88
    ischer
    -0.86
    inson
    -0.74
    agall
    -0.72
    andowski
    -0.72
    ials
    -0.71
    isks
    -0.71
    oslav
    -0.69
    instein
    -0.68
    POSITIVE LOGITS
     Nations
    0.92
     Races
    0.88
     Tournament
    0.75
     Championships
    0.73
     Nation
    0.70
     Tribe
    0.69
     Trading
    0.68
     tribe
    0.68
     Pag
    0.68
    keepers
    0.66
    Activations Density 0.010%

    No Known Activations