© 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. 19541
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "milk" in various contexts

    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
    288
    +0.17
    0.8%
    19
    +0.14
    0.6%
    347
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    19
    +0.17
    0.02
    347
    +0.14
    0.02
    288
    +0.10
    0.02
    Negative Logits
    izons
    -0.74
    SPONSORED
    -0.74
    vernment
    -0.73
    nces
    -0.73
    ISE
    -0.71
    âĸ¬
    -0.71
     lawy
    -0.71
    angers
    -0.70
    èª
    -0.69
    OPLE
    -0.66
    POSITIVE LOGITS
    weed
    1.28
    waukee
    1.08
    maid
    1.06
    fed
    0.92
    erton
    0.91
    nut
    0.89
     chocolate
    0.86
    fat
    0.84
     milk
    0.83
    haus
    0.83
    Activations Density 0.018%

    No Known Activations