© 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 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. 6509
    Prev
    Next
    INDEX
    Explanations

    baking instructions and ingredients for various recipes

    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
    640
    +0.23
    1.1%
    228
    +0.11
    0.5%
    390
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.03
    390
    +0.11
    0.03
    228
    +0.10
    0.03
    Negative Logits
    ¥µ
    -0.86
    assetsadobe
    -0.76
    aday
    -0.69
    ĸļ
    -0.69
    fm
    -0.67
    arcity
    -0.64
    hement
    -0.64
     experien
    -0.64
    leground
    -0.63
    lished
    -0.63
    POSITIVE LOGITS
    Ingredients
    1.17
     Instructions
    1.03
    ³³³
    1.00
    Instruct
    1.00
    ³³³³
    0.93
    Salt
    0.93
    Optional
    0.88
    Recipe
    0.86
    Method
    0.86
    ½
    0.85
    Activations Density 0.028%

    No Known Activations