© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions

    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
    447
    +0.28
    1.4%
    480
    +0.27
    1.4%
    481
    +0.22
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.28
    0.05
    739
    +0.27
    0.04
    128
    +0.22
    0.05
    Negative Logits
    asper
    -0.62
    iste
    -0.60
    bub
    -0.58
    ibble
    -0.57
    uct
    -0.56
    renheit
    -0.55
    abul
    -0.55
     Seym
    -0.54
    DIV
    -0.54
    abee
    -0.54
    POSITIVE LOGITS
     secondly
    1.22
     thence
    1.02
     therefore
    0.95
     consequently
    0.93
     thus
    0.92
     hence
    0.91
     furthermore
    0.84
     then
    0.83
     thereby
    0.82
     THEN
    0.81
    Activations Density 0.230%

    No Known Activations