© 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. 7727
    Prev
    Next
    INDEX
    Explanations

    actions related to organization, scheduling, and productivity

    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
    481
    +0.29
    1.4%
    588
    +0.10
    0.5%
    357
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.29
    0.05
    384
    +0.10
    0.04
    393
    +0.09
    0.06
    Negative Logits
     Variant
    -0.70
    icol
    -0.69
    isted
    -0.64
    ollar
    -0.63
    ledged
    -0.63
    lor
    -0.63
    nesty
    -0.62
     negro
    -0.60
    ©¶æ¥µ
    -0.60
    emin
    -0.60
    POSITIVE LOGITS
     chores
    0.94
     weddings
    0.93
     etc
    0.91
    etc
    0.89
     retrieving
    0.89
     storing
    0.89
     perform
    0.85
     browsing
    0.85
     assisting
    0.83
     communicate
    0.83
    Activations Density 0.343%

    No Known Activations