© 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. 153
    Prev
    Next
    INDEX
    Explanations

    information related to instructions and processes

    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
    298
    +0.11
    0.5%
    227
    +0.10
    0.5%
    727
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.03
    595
    +0.10
    0.02
    717
    +0.10
    0.02
    Negative Logits
    effic
    -0.74
    gradient
    -0.69
    culosis
    -0.69
    material
    -0.68
     proportions
    -0.65
    worthiness
    -0.64
    gery
    -0.63
    iform
    -0.63
    eatures
    -0.62
     Pengu
    -0.62
    POSITIVE LOGITS
     fray
    1.69
     chorus
    1.22
     ranks
    1.17
     bandwagon
    1.14
     dots
    0.92
     conversation
    0.84
     mailing
    0.82
     discussion
    0.82
     exodus
    0.80
     fold
    0.76
    Activations Density 0.102%

    No Known Activations