© 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 EvalsExportsinterp-engineNEWAPI 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. 20850
    Prev
    Next
    INDEX
    Explanations

    information related to weather events and storm categories

    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
    447
    +0.15
    0.7%
    481
    +0.13
    0.6%
    70
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.06
    724
    +0.13
    0.05
    460
    +0.10
    0.04
    Negative Logits
    ometric
    -0.64
    ãĤ±
    -0.63
    estamp
    -0.63
     obser
    -0.57
    istor
    -0.55
    ellar
    -0.53
    ogram
    -0.53
     palette
    -0.53
    YN
    -0.53
     convol
    -0.53
    POSITIVE LOGITS
    outs
    0.77
    dates
    0.77
    waves
    0.76
    rooms
    0.73
    planes
    0.73
    utics
    0.72
    smanship
    0.72
    pieces
    0.72
     Dragonbound
    0.71
    livion
    0.71
    Activations Density 0.296%

    No Known Activations