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. 2-RES-JB
    6. 10109
    Prev
    Next
    INDEX
    Explanations

    the name "Willie" appearing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those in notable roles or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ariat
    -0.83
    yrinth
    -0.76
    ocrine
    -0.75
    actionDate
    -0.75
    izoph
    -0.72
    ¥ŀ
    -0.71
     contiguous
    -0.69
    orescent
    -0.69
    ocaust
    -0.68
    internet
    -0.68
    POSITIVE LOGITS
     Willie
    1.25
     Nelson
    0.92
    sburg
    0.82
     Horton
    0.81
     Dixon
    0.79
     Vander
    0.78
     Robertson
    0.76
     Thornton
    0.76
     Armstrong
    0.75
    lette
    0.75
    Activations Density 0.006%

    No Known Activations