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. 320
    Prev
    Next
    INDEX
    Explanations

    news articles discussing legal cases and political decisions

    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
    640
    +0.17
    0.8%
    373
    +0.16
    0.7%
    709
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.04
    160
    +0.16
    0.03
    373
    +0.11
    -0.01
    Negative Logits
     oun
    -0.77
    hement
    -0.68
     intermedi
    -0.68
     respectively
    -0.66
     ende
    -0.66
     whichever
    -0.64
    ector
    -0.61
     supervised
    -0.61
    ¡
    -0.60
     hooked
    -0.60
    POSITIVE LOGITS
    âĢ¢
    0.95
    Comments
    0.94
    âϦ
    0.91
    Woman
    0.90
    âĸº
    0.90
    Tags
    0.85
    Feature
    0.83
    LIST
    0.82
    Recent
    0.81
    Watch
    0.81
    Activations Density 0.064%

    No Known Activations