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 · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11711
    Prev
    Next
    INDEX
    Explanations

    running backs and wide receivers in American football

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    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

    Neuron Alignment
    Index
    Value
    % of L₁
    525
    +0.10
    0.5%
    722
    +0.10
    0.5%
    502
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.10
    0.06
    659
    +0.10
    0.06
    700
    +0.10
    0.06
    Negative Logits
     Rowling
    -0.83
     Feminist
    -0.75
     Gloria
    -0.75
     censor
    -0.68
     Lanka
    -0.68
     Prohibition
    -0.68
     capitalists
    -0.66
     Wem
    -0.66
     Canaver
    -0.66
     fundament
    -0.65
    POSITIVE LOGITS
     Jr
    1.18
     III
    0.94
     teammate
    0.93
     rookie
    0.92
     injury
    0.91
     injured
    0.90
     Rookie
    0.89
     waivers
    0.87
     undrafted
    0.86
     intercepted
    0.86
    Activations Density 0.193%

    No Known Activations