© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12096
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical information from text

    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
    87
    +0.26
    1.4%
    71
    +0.12
    0.6%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.26
    0.10
    223
    +0.12
    0.09
    310
    +0.11
    0.09
    Negative Logits
    laws
    -0.63
    stakes
    -0.61
    law
    -0.51
    evin
    -0.50
    bred
    -0.50
    venge
    -0.50
    Ħ¢
    -0.49
    oried
    -0.49
     brav
    -0.49
     Doodle
    -0.48
    POSITIVE LOGITS
     tonnes
    0.84
    %
    0.81
     percent
    0.80
     per
    0.77
     kil
    0.76
     fewer
    0.76
     lbs
    0.76
     ±
    0.76
     apiece
    0.76
     kilograms
    0.75
    Activations Density 0.380%

    No Known Activations