© 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. 6553
    Prev
    Next
    INDEX
    Explanations

    specific names of sports players

    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
    240
    +0.10
    0.5%
    388
    +0.10
    0.4%
    357
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    232
    +0.10
    0.03
    288
    +0.10
    0.03
    Negative Logits
    ITH
    -0.82
    ä¹ĭ
    -0.69
    ansom
    -0.66
    IZ
    -0.64
    SOURCE
    -0.62
    OSP
    -0.61
    WORK
    -0.60
    IDER
    -0.59
    ãģĦ
    -0.59
     margins
    -0.58
    POSITIVE LOGITS
    ebin
    1.12
    inho
    1.08
    urers
    1.06
    ure
    1.01
    urations
    0.97
    vre
    0.93
    rue
    0.91
    rio
    0.89
    urer
    0.89
    esy
    0.87
    Activations Density 0.064%

    No Known Activations