© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7387
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities

    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
    399
    +0.13
    0.6%
    748
    +0.10
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    748
    +0.13
    0.06
    344
    +0.10
    0.07
    399
    +0.10
    0.05
    Negative Logits
    needs
    -0.82
    urgy
    -0.78
    biology
    -0.74
    obin
    -0.74
    $$
    -0.73
    trap
    -0.70
    doesn
    -0.69
    vantage
    -0.69
    amaru
    -0.68
    urden
    -0.67
    POSITIVE LOGITS
     dozen
    1.13
    teenth
    1.12
    teen
    1.02
     unnamed
    1.02
     prominent
    1.01
     successive
    1.01
     hundred
    0.97
     separate
    0.97
     consecutive
    0.96
     unidentified
    0.91
    Activations Density 0.186%

    No Known Activations