© 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. 67
    Prev
    Next
    INDEX
    Explanations

    references to ranked lists and top positions in a specific category

    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
    194
    +0.14
    0.6%
    131
    +0.10
    0.5%
    182
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.14
    0.04
    278
    +0.10
    0.04
    116
    +0.09
    0.03
    Negative Logits
    ierrez
    -0.73
    ework
    -0.72
     curl
    -0.68
    ensibly
    -0.66
    raid
    -0.65
    amar
    -0.64
    dding
    -0.64
    ctor
    -0.63
    rition
    -0.63
    gif
    -0.62
    POSITIVE LOGITS
    ottest
    0.89
     Worst
    0.85
     finalists
    0.84
     Highly
    0.78
     Greatest
    0.77
     highest
    0.77
     smartest
    0.76
     trending
    0.76
     safest
    0.74
     globally
    0.73
    Activations Density 0.252%

    No Known Activations