© 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. 12309
    Prev
    Next
    INDEX
    Explanations

    references to disc golf and handball

    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
    +0.19
    0.9%
    481
    +0.13
    0.6%
    153
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.06
    153
    +0.13
    0.04
    575
    +0.10
    0.04
    Negative Logits
     Rudolph
    -0.70
     Dull
    -0.67
     clot
    -0.67
    pex
    -0.67
    \/\/
    -0.65
    oeuv
    -0.64
    ãĤ½
    -0.64
    anamo
    -0.61
    staking
    -0.60
     Luthor
    -0.60
    POSITIVE LOGITS
     royalty
    0.91
     competitions
    0.83
     enthusiasts
    0.81
     careers
    0.81
     renaissance
    0.81
     leagues
    0.80
     clubs
    0.79
     fandom
    0.79
     pioneers
    0.79
     royalties
    0.78
    Activations Density 0.191%

    No Known Activations