© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11940
    Prev
    Next
    INDEX
    Explanations

    information related to sports players, their attributes, injuries, and performance statistics

    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
    373
    +0.15
    0.7%
    99
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.15
    0.02
    99
    +0.10
    0.02
    545
    +0.09
    0.02
    Negative Logits
    oys
    -0.67
    ezvous
    -0.65
     Governments
    -0.65
    enment
    -0.64
    bringer
    -0.61
    ictions
    -0.61
     NHS
    -0.61
    icable
    -0.60
    elt
    -0.59
     Sel
    -0.59
    POSITIVE LOGITS
     tall
    0.98
    tall
    0.82
     taller
    0.80
    inches
    0.74
    perfect
    0.72
    quart
    0.71
    rafted
    0.70
    arious
    0.67
    omething
    0.65
     floppy
    0.65
    Activations Density 0.033%

    No Known Activations