© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18379
    Prev
    Next
    INDEX
    Explanations

    government agencies, departments, and organizations

    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
    120
    +0.12
    0.6%
    53
    +0.11
    0.5%
    409
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.02
    120
    +0.11
    0.02
    287
    +0.10
    0.02
    Negative Logits
    gow
    -0.77
    auga
    -0.75
    respective
    -0.69
    warts
    -0.65
    borgh
    -0.65
    ppa
    -0.65
    uve
    -0.64
    piece
    -0.63
    ertodd
    -0.63
    rise
    -0.62
    POSITIVE LOGITS
     Statistics
    1.00
     Investigation
    0.96
     Alcohol
    0.94
     Forestry
    0.89
     Meteor
    0.87
     Statistical
    0.87
     Transportation
    0.84
     Investigative
    0.84
    ãĥĥãĥĪ
    0.83
     Customs
    0.83
    Activations Density 0.026%

    No Known Activations