© 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. 18712
    Prev
    Next
    INDEX
    Explanations

    technical terms related to woodworking and movies, as well as some Spanish words related to criminal justice

    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
    87
    +0.43
    2.5%
    756
    +0.17
    1.0%
    288
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.43
    0.09
    87
    +0.17
    -0.01
    326
    +0.08
    0.07
    Negative Logits
    ells
    -0.65
    berman
    -0.65
    names
    -0.62
    unal
    -0.62
    laws
    -0.62
    abase
    -0.61
    parse
    -0.61
    fixes
    -0.60
    href
    -0.60
    rations
    -0.59
    POSITIVE LOGITS
     Aph
    0.52
     extraord
    0.49
     APR
    0.48
     Gent
    0.47
     Cu
    0.47
     Soph
    0.47
     overlooking
    0.46
     flats
    0.46
     Pf
    0.46
     Messi
    0.45
    Activations Density 0.611%

    No Known Activations