© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3992
    Prev
    Next
    INDEX
    Explanations

    components and features related to building or modifying a vehicle

    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
    435
    +0.12
    0.5%
    475
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.05
    288
    +0.11
    0.05
    326
    +0.11
    0.04
    Negative Logits
    vernment
    -0.83
    emonic
    -0.78
     largeDownload
    -0.77
     WATCHED
    -0.76
    ocument
    -0.75
    prison
    -0.74
    zynski
    -0.74
     Petr
    -0.71
     Prison
    -0.71
    inical
    -0.71
    POSITIVE LOGITS
     assembly
    1.07
     configuration
    1.03
     diameter
    1.00
     configurations
    0.96
     specification
    0.96
     manufacturer
    0.96
     protector
    0.95
     width
    0.93
     calibration
    0.93
     specifications
    0.93
    Activations Density 0.163%

    No Known Activations