Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8389
    Prev
    Next
    INDEX
    Explanations

    percentage values and ranking words

    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
    447
    +0.29
    1.5%
    480
    +0.28
    1.4%
    87
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.29
    0.06
    480
    +0.28
    0.02
    464
    +0.17
    0.05
    Negative Logits
     Seym
    -0.63
     accord
    -0.53
    Category
    -0.53
     Moroc
    -0.52
     Azerb
    -0.52
    Template
    -0.50
    Ware
    -0.50
    gage
    -0.50
     Vaugh
    -0.49
    herer
    -0.49
    POSITIVE LOGITS
     alike
    0.94
     thereof
    0.83
     thereafter
    0.75
     thereto
    0.71
     respectively
    0.70
    cellaneous
    0.66
     consequ
    0.59
     versa
    0.57
     accordingly
    0.57
     therein
    0.57
    Activations Density 0.379%

    No Known Activations