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

    Neuronpedia

    Jacobian LensNEW
    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. 18108
    Prev
    Next
    INDEX
    Explanations

    time-related terms and deadlines

    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
    512
    +0.10
    0.4%
    433
    +0.09
    0.4%
    132
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.10
    0.04
    546
    +0.09
    0.03
    746
    +0.09
    0.03
    Negative Logits
     Cosponsors
    -0.79
    named
    -0.75
    galitarian
    -0.74
    ronics
    -0.71
    artisan
    -0.70
    BIL
    -0.68
    ãĤ´
    -0.68
    BAT
    -0.67
     Generic
    -0.66
    ãĤ¶
    -0.66
    POSITIVE LOGITS
     weekends
    1.06
     evenings
    1.06
     vacations
    1.04
     holidays
    1.02
     mornings
    1.01
    morning
    1.00
     onwards
    0.94
     Sundays
    0.94
     autumn
    0.91
     Thurs
    0.91
    Activations Density 0.154%

    No Known Activations