© 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 EvalsExportsinterp-engineNEWAPI 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. 13271
    Prev
    Next
    INDEX
    Explanations

    technical terms related to legal proceedings and equipment

    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
    288
    +0.11
    0.5%
    87
    +0.10
    0.5%
    415
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.08
    575
    +0.10
    0.07
    459
    +0.10
    0.06
    Negative Logits
    姫
    -0.85
    packages
    -0.77
    sites
    -0.76
    values
    -0.76
     channels
    -0.74
    NetMessage
    -0.70
    paces
    -0.68
    events
    -0.68
     Methods
    -0.67
    thumbnails
    -0.67
    POSITIVE LOGITS
     consisting
    1.00
     akin
    0.91
     reminiscent
    0.81
     resembling
    0.81
     named
    0.79
     wherein
    0.78
     nicknamed
    0.77
     thats
    0.77
     whose
    0.77
     comprised
    0.74
    Activations Density 0.410%

    No Known Activations