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 1536
    5. 8-RES_FS1536-JB
    6. 930
    Prev
    Next
    INDEX
    Explanations

    references to political and social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    159
    +0.17
    0.8%
    393
    +0.14
    0.6%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.17
    0.19
    95
    +0.14
    0.10
    606
    +0.11
    0.11
    Negative Logits
    aws
    -0.77
    ARS
    -0.76
    ickets
    -0.73
    unk
    -0.72
    isms
    -0.71
    gans
    -0.70
    icons
    -0.69
    adle
    -0.69
    ivas
    -0.69
    acers
    -0.69
    POSITIVE LOGITS
     week
    1.13
     year
    1.00
     latest
    1.00
     trope
    0.99
     particular
    0.98
     article
    0.98
     month
    0.95
     weekend
    0.92
     incarnation
    0.90
     arrangement
    0.88
    Activations Density 0.902%

    No Known Activations