© 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. 21287
    Prev
    Next
    INDEX
    Explanations

    descriptions related to injuries and penalties in sports

    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
    481
    +0.15
    0.7%
    328
    +0.09
    0.4%
    244
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.15
    0.04
    268
    +0.09
    0.03
    16
    +0.09
    0.04
    Negative Logits
    ographies
    -0.89
    izons
    -0.83
    profits
    -0.76
     inclusive
    -0.74
    Pros
    -0.74
    Demand
    -0.73
    soType
    -0.73
    isSpecialOrderable
    -0.73
    ensus
    -0.71
     Governments
    -0.71
    POSITIVE LOGITS
     accidentally
    1.22
     injuring
    1.17
     altercation
    1.10
     mishand
    1.09
     malfunction
    1.07
     accident
    1.06
     careless
    1.01
     spilled
    1.01
     improperly
    1.00
     injure
    0.99
    Activations Density 0.551%

    No Known Activations