© 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. 22493
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of basketball players and related entities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    201
    +0.10
    0.5%
    365
    +0.10
    0.5%
    685
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.03
    659
    +0.10
    0.03
    343
    +0.10
    0.03
    Negative Logits
     Manson
    -0.72
    >>>>>>>>
    -0.69
    GROUP
    -0.67
    ãĥĩãĤ£
    -0.67
    ESE
    -0.65
    FFFF
    -0.65
    ++++
    -0.65
    head
    -0.65
     Playboy
    -0.64
     cigarette
    -0.63
    POSITIVE LOGITS
    iour
    0.98
    endo
    0.92
    lar
    0.89
    olulu
    0.89
    hern
    0.88
    atoon
    0.87
    onite
    0.86
    sie
    0.85
    oji
    0.85
    igel
    0.84
    Activations Density 0.061%

    No Known Activations