© 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. 21232
    Prev
    Next
    INDEX
    Explanations

    words relating to sports, competitions, and writing styles

    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
    +0.31
    1.5%
    480
    +0.23
    1.1%
    481
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.31
    0.04
    480
    +0.23
    0.01
    266
    +0.17
    0.03
    Negative Logits
     Oval
    -0.64
     Borders
    -0.62
     Mellon
    -0.59
     Byr
    -0.59
     Niet
    -0.56
     Kelley
    -0.56
     Cay
    -0.55
     Nare
    -0.55
     Kik
    -0.55
     Jagu
    -0.55
    POSITIVE LOGITS
    mosp
    0.89
    _
    0.76
    irez
    0.74
    etheless
    0.74
    lement
    0.72
    coins
    0.71
    tenance
    0.71
    clair
    0.71
    posure
    0.70
    mouse
    0.69
    Activations Density 0.117%

    No Known Activations