© 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 EvalsExportsAPI 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. 12417
    Prev
    Next
    INDEX
    Explanations

    names indicated by the prefix "De"

    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
    525
    +0.11
    0.5%
    119
    +0.11
    0.5%
    733
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.07
    525
    +0.11
    0.04
    232
    +0.10
    0.04
    Negative Logits
     Dhabi
    -0.74
     Romanian
    -0.72
    âĶĢâĶĢ
    -0.68
     UA
    -0.66
     Ai
    -0.64
     Korra
    -0.64
     Croatian
    -0.63
     Kath
    -0.63
     Paulo
    -0.63
     Sina
    -0.62
    POSITIVE LOGITS
    antz
    0.93
    atch
    0.78
    idge
    0.74
    fork
    0.74
    steen
    0.74
    scl
    0.73
    ĵĺ
    0.72
    otta
    0.69
    zinski
    0.69
    hol
    0.68
    Activations Density 0.115%

    No Known Activations