© 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 12288
    5. 8-RES_FS12288-JB
    6. 9451
    Prev
    Next
    INDEX
    Explanations

    critique or call to action against specific reports or beliefs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    408
    +0.10
    0.5%
    566
    +0.10
    0.4%
    438
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.10
    0.04
    733
    +0.10
    0.03
    203
    +0.09
    0.03
    Negative Logits
    uay
    -0.80
    osterone
    -0.78
    ocene
    -0.77
    rick
    -0.75
    opian
    -0.74
    oil
    -0.73
    hene
    -0.72
     Murd
    -0.72
    ellen
    -0.72
    otta
    -0.71
    POSITIVE LOGITS
     matters
    0.88
    ties
    0.82
    ities
    0.79
     kinds
    0.78
     drastic
    0.78
     minded
    0.77
     phenomena
    0.76
     considerations
    0.75
     establishments
    0.75
     endeavors
    0.74
    Activations Density 0.070%

    No Known Activations