© 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. 16669
    Prev
    Next
    INDEX
    Explanations

    functions and numerical operations within a code context

    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
    480
    +0.52
    2.8%
    266
    +0.16
    0.9%
    87
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.03
    266
    +0.16
    0.08
    678
    +0.15
    0.05
    Negative Logits
    ourcing
    -0.67
     anecd
    -0.65
     millenn
    -0.60
     resurg
    -0.60
     enthusi
    -0.59
     fostering
    -0.58
    kef
    -0.57
    ONSORED
    -0.57
     nurs
    -0.56
     Moroc
    -0.55
    POSITIVE LOGITS
     specified
    0.93
     integer
    0.81
     desired
    0.79
     integers
    0.78
     \(
    0.77
     decimal
    0.75
     input
    0.74
     pixels
    0.74
     tiles
    0.73
     \'
    0.73
    Activations Density 0.758%

    No Known Activations