© 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. 12844
    Prev
    Next
    INDEX
    Explanations

    articles that are particularly old or from an archive

    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
    498
    +0.10
    0.5%
    182
    +0.10
    0.5%
    532
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.10
    0.04
    498
    +0.10
    0.03
    739
    +0.09
    0.02
    Negative Logits
     looms
    -0.89
    $$$$
    -0.70
    ths
    -0.67
    kees
    -0.63
    stones
    -0.62
    auga
    -0.62
     Mexicans
    -0.62
     torches
    -0.61
    cknow
    -0.61
     charms
    -0.60
    POSITIVE LOGITS
     sponsored
    0.88
     archived
    0.85
     reprinted
    0.84
     excerpt
    0.84
     deprecated
    0.82
     edited
    0.82
     updated
    0.79
     reviewed
    0.78
     adapted
    0.77
     reproduced
    0.73
    Activations Density 0.110%

    No Known Activations