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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11885
    Prev
    Next
    INDEX
    Explanations

    references to incidents, investigations, and reports about various events or occurrences

    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
    362
    +0.14
    0.6%
    467
    +0.11
    0.5%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.07
    371
    +0.11
    0.07
    403
    +0.09
    0.06
    Negative Logits
    alpha
    -0.75
    γ
    -0.75
    archy
    -0.74
    Pac
    -0.74
    ratulations
    -0.73
    idav
    -0.72
    HTML
    -0.69
    ption
    -0.67
    zyk
    -0.67
    FTWARE
    -0.67
    POSITIVE LOGITS
     least
    1.20
    onement
    1.03
     hotels
    0.96
     airports
    0.94
     home
    0.90
     Disneyland
    0.88
     cafes
    0.87
     restaurants
    0.85
     festivals
    0.84
     stake
    0.83
    Activations Density 0.210%

    No Known Activations