© 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. 15934
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of persons or locations

    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
    506
    +0.13
    0.6%
    447
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.04
    659
    +0.12
    0.03
    314
    +0.10
    0.01
    Negative Logits
     OCT
    -0.78
     PAR
    -0.78
     IX
    -0.76
    WINDOWS
    -0.76
     DOS
    -0.74
     SOU
    -0.72
    س
    -0.69
     Beats
    -0.68
     +++
    -0.68
    大
    -0.66
    POSITIVE LOGITS
    er
    1.79
    ers
    1.57
    ER
    1.45
    erm
    1.31
    ership
    1.29
    erd
    1.22
    ering
    1.22
    eric
    1.22
    eri
    1.22
    erk
    1.17
    Activations Density 0.095%

    No Known Activations