© 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. 10433
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational membership

    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
    679
    +0.14
    0.7%
    711
    +0.10
    0.4%
    668
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.14
    0.02
    679
    +0.10
    0.03
    485
    +0.09
    0.02
    Negative Logits
    enegger
    -0.82
    bows
    -0.72
    ources
    -0.69
    orsi
    -0.64
    obiles
    -0.64
    urses
    -0.63
    ricanes
    -0.63
    uras
    -0.62
    anche
    -0.62
    itars
    -0.62
    POSITIVE LOGITS
     of
    0.94
    board
    0.89
     thereof
    0.86
    hips
    0.82
    member
    0.80
    holder
    0.76
    Joined
    0.75
     member
    0.73
    leader
    0.70
    Activity
    0.70
    Activations Density 0.028%

    No Known Activations