© 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. 18928
    Prev
    Next
    INDEX
    Explanations

    mentions of nutrition and food-related health issues

    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
    717
    +0.12
    0.5%
    543
    +0.11
    0.5%
    393
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.05
    732
    +0.11
    0.04
    393
    +0.10
    0.05
    Negative Logits
     pregn
    -0.69
    ynamic
    -0.68
    ogi
    -0.68
    atical
    -0.66
    Lago
    -0.65
    sbm
    -0.65
    igmatic
    -0.65
    UGH
    -0.64
    ysis
    -0.64
    ģ«
    -0.64
    POSITIVE LOGITS
     mortar
    0.71
     youth
    0.64
    Lab
    0.62
     Wales
    0.62
     beverages
    0.62
    cius
    0.61
     beverage
    0.61
     Fey
    0.60
     Entered
    0.60
     Labrador
    0.60
    Activations Density 0.204%

    No Known Activations