© 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. 14442
    Prev
    Next
    INDEX
    Explanations

    instances where someone is tying or equalling a record, score, or game

    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
    +0.13
    0.6%
    704
    +0.10
    0.5%
    648
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.13
    0.02
    274
    +0.10
    0.02
    761
    +0.10
    0.02
    Negative Logits
    xit
    -0.89
    abis
    -0.68
    sbm
    -0.67
    anmar
    -0.65
    markets
    -0.64
    rians
    -0.64
    ffect
    -0.64
    dor
    -0.62
    lene
    -0.60
    inelli
    -0.60
    POSITIVE LOGITS
    ieth
    0.79
    unts
    0.70
     clin
    0.67
     digits
    0.64
     tying
    0.64
    uable
    0.62
     tripled
    0.62
    break
    0.61
     breaker
    0.61
     unbeat
    0.61
    Activations Density 0.093%

    No Known Activations