© 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 EvalsExportsinterp-engineNEWAPI 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. 16194
    Prev
    Next
    INDEX
    Explanations

    financial information such as stock prices, futures, and market records

    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
    722
    +0.11
    0.5%
    724
    +0.10
    0.5%
    132
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.03
    178
    +0.10
    0.03
    132
    +0.10
    0.03
    Negative Logits
    oute
    -0.75
     superior
    -0.73
    cipl
    -0.72
    argon
    -0.66
    ategories
    -0.66
    athe
    -0.60
    avering
    -0.60
    oked
    -0.59
     nos
    -0.58
    orge
    -0.58
    POSITIVE LOGITS
     1929
    0.77
     July
    0.75
     September
    0.75
     August
    0.75
     amid
    0.70
     December
    0.70
     April
    0.69
     October
    0.69
    cember
    0.69
     Gallup
    0.69
    Activations Density 0.113%

    No Known Activations