© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9283
    Prev
    Next
    INDEX
    Explanations

    keywords related to various foods (pear, nutmeg, cone, snake, gum, corn, cream) and a body part (waist)

    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
    447
    +0.29
    1.5%
    480
    +0.28
    1.5%
    481
    +0.25
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.29
    0.08
    266
    +0.28
    0.06
    85
    +0.25
    0.07
    Negative Logits
    SPONSORED
    -0.75
     Fundamental
    -0.66
    CLASSIFIED
    -0.66
     Borders
    -0.65
     Territories
    -0.63
     Narr
    -0.61
    Interstitial
    -0.58
     DPR
    -0.58
    Demand
    -0.58
     Reason
    -0.57
    POSITIVE LOGITS
    cakes
    0.85
    yp
    0.73
    weed
    0.71
    bum
    0.71
    cake
    0.71
    fort
    0.69
    coin
    0.69
    soft
    0.69
    map
    0.65
    bow
    0.65
    Activations Density 0.315%

    No Known Activations