Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 386
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions in recipe-like text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    145
    +0.12
    0.6%
    238
    +0.11
    0.5%
    59
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.17
    314
    +0.11
    -0.00
    288
    +0.10
    0.17
    Negative Logits
    ELS
    -0.82
    endor
    -0.75
    ures
    -0.71
    ERG
    -0.70
    ĨĴ
    -0.69
    ouls
    -0.68
    ured
    -0.68
    etts
    -0.67
    ħĭ
    -0.66
    EMS
    -0.66
    POSITIVE LOGITS
    ror
    1.17
    rier
    1.17
    rors
    1.13
    rington
    1.09
    riage
    1.08
    thur
    1.08
    rigan
    1.06
    rible
    1.06
    riers
    1.06
    izons
    1.02
    Activations Density 4.621%

    No Known Activations