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. 19177
    Prev
    Next
    INDEX
    Explanations

    adjectives related to quality or characteristics of things

    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
    545
    +0.11
    0.5%
    322
    +0.10
    0.5%
    642
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.11
    0.03
    322
    +0.10
    0.03
    355
    +0.09
    0.03
    Negative Logits
    irl
    -0.71
    jri
    -0.69
    ixtape
    -0.68
     Continent
    -0.67
    RN
    -0.66
    ramid
    -0.65
    xit
    -0.63
    gettable
    -0.63
    ulner
    -0.62
    agonist
    -0.62
    POSITIVE LOGITS
     increments
    1.13
     proportions
    1.03
     fashion
    0.97
     circumstances
    0.95
     chronological
    0.93
     shape
    0.92
     circles
    0.92
     accordance
    0.89
     haste
    0.89
     terms
    0.88
    Activations Density 0.109%

    No Known Activations