© 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. 15888
    Prev
    Next
    INDEX
    Explanations

    references to specific names, especially related to sports

    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
    464
    +0.12
    0.6%
    447
    +0.11
    0.5%
    343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.12
    0.01
    190
    +0.11
    0.01
    343
    +0.11
    0.01
    Negative Logits
    ablishment
    -0.93
    ional
    -0.90
    imates
    -0.85
    lishes
    -0.85
    insula
    -0.83
    iment
    -0.74
    ãĥ´ãĤ¡
    -0.72
    atively
    -0.71
    alion
    -0.70
    ACTION
    -0.69
    POSITIVE LOGITS
     Bryant
    1.24
    wana
    0.77
    hoff
    0.74
     Jr
    0.72
    hurst
    0.70
     Stadium
    0.70
     Jennings
    0.70
    sey
    0.70
     Harden
    0.69
     Nelson
    0.69
    Activations Density 0.019%

    No Known Activations