© 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. 20745
    Prev
    Next
    INDEX
    Explanations

    descriptions of business models and strategies

    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
    393
    +0.12
    0.6%
    462
    +0.10
    0.5%
    164
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.12
    0.07
    694
    +0.10
    0.04
    530
    +0.10
    0.04
    Negative Logits
    ":"/
    -0.86
    imester
    -0.78
    erity
    -0.68
    ãĥ¼ãĤ¯
    -0.67
    jected
    -0.63
    Ö
    -0.63
    İ
    -0.63
    :\
    -0.62
    PIN
    -0.62
    ajor
    -0.62
    POSITIVE LOGITS
     etc
    2.14
    etc
    1.64
     ect
    1.13
     et
    0.89
     respectively
    0.80
    ...)
    0.78
     blah
    0.77
     assorted
    0.76
    âĢ¦)
    0.73
     prest
    0.73
    Activations Density 0.199%

    No Known Activations