© 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. 10185
    Prev
    Next
    INDEX
    Explanations

    words related to infrastructure and maintenance projects

    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
    238
    +0.14
    0.6%
    663
    +0.12
    0.5%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.02
    663
    +0.12
    0.01
    238
    +0.11
    0.01
    Negative Logits
    ãĥ¯ãĥ³
    -0.80
    lain
    -0.79
    lift
    -0.78
    ãĤ°
    -0.78
    */(
    -0.72
    mill
    -0.72
    MIT
    -0.71
     Horizon
    -0.69
    lished
    -0.69
    spin
    -0.69
    POSITIVE LOGITS
    asca
    0.97
    yah
    0.96
    aceous
    0.94
    aments
    0.91
    atory
    0.89
    ensis
    0.87
    ptin
    0.85
    ère
    0.82
    ppy
    0.81
    ory
    0.81
    Activations Density 0.033%

    No Known Activations