© 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 12288
    9. 8-RES_FS12288-JB
    11. 10478
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement, specifically climbing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    659
    +0.12
    0.5%
    343
    +0.09
    0.4%
    326
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    335
    +0.09
    0.03
    41
    +0.09
    0.02
    Negative Logits
    ãĥĨãĤ£
    -0.70
    rums
    -0.68
    iveness
    -0.67
    onom
    -0.65
    rum
    -0.63
    eval
    -0.63
    zig
    -0.63
    Hart
    -0.62
    invoke
    -0.61
    aments
    -0.61
    POSITIVE LOGITS
     Everest
    1.11
     footh
    1.06
     stairs
    1.03
     ladder
    0.94
     climb
    0.94
     altitude
    0.93
     climbing
    0.92
     mountains
    0.90
     aboard
    0.89
    acus
    0.88
    Activations Density 0.114%

    No Known Activations