© 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. 9625
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology, genres of literature, and governmental initiatives

    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
    713
    +0.14
    0.7%
    514
    +0.10
    0.5%
    545
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.02
    514
    +0.10
    0.03
    713
    +0.10
    0.03
    Negative Logits
     cath
    -0.69
    assian
    -0.67
     objective
    -0.66
     distraction
    -0.63
     Tsukuyomi
    -0.63
     extreme
    -0.62
     congen
    -0.60
     Baz
    -0.60
     divergence
    -0.60
     limitation
    -0.59
    POSITIVE LOGITS
    handedly
    1.08
    etheless
    1.01
    rily
    0.97
    efully
    0.97
    rely
    0.94
    heartedly
    0.94
    wrote
    0.93
    ounced
    0.90
    hered
    0.90
    ighed
    0.90
    Activations Density 0.161%

    No Known Activations