© 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. 21126
    Prev
    Next
    INDEX
    Explanations

    information related to programming, specifically focusing on functions and compiling programs

    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
    255
    +0.10
    0.5%
    314
    +0.09
    0.4%
    214
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.05
    255
    +0.09
    0.04
    678
    +0.09
    0.03
    Negative Logits
     Borders
    -0.77
    lik
    -0.76
     ceilings
    -0.76
     liv
    -0.72
     Pau
    -0.72
     dwindling
    -0.72
     modesty
    -0.71
     maternity
    -0.71
    united
    -0.70
     beds
    -0.70
    POSITIVE LOGITS
     execute
    1.23
    execute
    1.15
     executes
    1.15
     executing
    1.07
     handler
    1.04
    Exec
    1.03
     args
    1.01
     executed
    1.00
     invocation
    0.99
     execution
    0.98
    Activations Density 0.313%

    No Known Activations