© 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. 11961
    Prev
    Next
    INDEX
    Explanations

    the word "mo" with high activation values

    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
    +0.11
    0.5%
    745
    +0.10
    0.5%
    254
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.01
    174
    +0.10
    0.02
    535
    +0.08
    0.01
    Negative Logits
     Scand
    -0.64
    emort
    -0.59
     circles
    -0.58
    ©¶æ
    -0.55
     Sutherland
    -0.54
    utenberg
    -0.52
     quarters
    -0.52
     lodge
    -0.52
    hospital
    -0.51
     pg
    -0.51
    POSITIVE LOGITS
    ighed
    0.94
    oused
    0.92
    ousing
    0.89
    ciating
    0.86
    asion
    0.86
    lement
    0.84
    ufact
    0.84
    ishment
    0.83
    uates
    0.82
    itably
    0.82
    Activations Density 0.064%

    No Known Activations