© 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 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. 5931
    Prev
    Next
    INDEX
    Explanations

    references to business strategies and plans

    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
    640
    +0.30
    1.4%
    370
    +0.09
    0.4%
    694
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.30
    0.06
    94
    +0.09
    0.04
    245
    +0.09
    0.03
    Negative Logits
    hement
    -0.66
     estranged
    -0.64
    abouts
    -0.58
    ction
    -0.58
    ardless
    -0.57
     Gaal
    -0.56
     Cent
    -0.56
    tsky
    -0.56
     proud
    -0.56
     accordingly
    -0.55
    POSITIVE LOGITS
    âĹı
    1.11
    ³³³
    0.99
    ³³³³
    0.97
    ³³³³³³³³³³³³³³³³
    0.95
    ³³³³³³³³
    0.93
    ·
    0.88
    âľ
    0.85
    ³³
    0.82
    âĺħ
    0.81
    âĸł
    0.79
    Activations Density 0.073%

    No Known Activations