© 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. 20587
    Prev
    Next
    INDEX
    Explanations

    personal names

    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
    481
    +0.17
    0.8%
    314
    +0.12
    0.6%
    731
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    696
    +0.17
    0.04
    314
    +0.12
    0.00
    18
    +0.11
    0.03
    Negative Logits
     EFF
    -0.75
     behav
    -0.73
     iP
    -0.72
     SAN
    -0.71
     distingu
    -0.71
     ESP
    -0.70
     Azerbai
    -0.68
     IPM
    -0.68
     hurd
    -0.67
     ����
    -0.67
    POSITIVE LOGITS
    utenberg
    0.96
    raq
    0.93
    iland
    0.92
    ulo
    0.91
    zon
    0.90
    kin
    0.89
    icum
    0.89
    oire
    0.87
    eda
    0.86
    ida
    0.85
    Activations Density 0.155%

    No Known Activations