© 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. 14134
    Prev
    Next
    INDEX
    Explanations

    keywords related to clicks on buttons or links

    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
    314
    +0.12
    0.5%
    70
    +0.10
    0.5%
    633
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    604
    +0.12
    0.02
    70
    +0.10
    0.02
    633
    +0.10
    0.02
    Negative Logits
     Yard
    -0.70
    egal
    -0.67
     Variety
    -0.66
     Chancellor
    -0.63
     Scotia
    -0.62
    utive
    -0.62
    ZA
    -0.59
     Catalonia
    -0.58
     Arabs
    -0.58
     Berk
    -0.58
    POSITIVE LOGITS
    lish
    0.86
    prints
    0.84
    ety
    0.84
    through
    0.81
    pad
    0.81
    wheel
    0.80
    dress
    0.80
    ername
    0.77
    esome
    0.75
    antry
    0.74
    Activations Density 0.019%

    No Known Activations