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 49152
    5. 8-RES_FS49152-JB
    6. 43178
    Prev
    Next
    INDEX
    Explanations

    references to types of agricultural products and their implications in labor and health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.15
    0.7%
    549
    +0.13
    0.6%
    52
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.01
    326
    +0.13
    0.01
    549
    +0.11
    0.01
    Negative Logits
    stakes
    -0.82
    eal
    -0.80
    zona
    -0.79
    furt
    -0.79
    ansky
    -0.77
    nings
    -0.75
    onym
    -0.74
    onymous
    -0.73
    endez
    -0.73
    vy
    -0.73
    POSITIVE LOGITS
     cane
    1.14
     plantation
    1.00
     plantations
    1.00
     sugar
    0.89
     juice
    0.86
     farming
    0.82
     syrup
    0.81
     quarry
    0.81
    apple
    0.81
     labou
    0.81
    Activations Density 0.005%

    No Known Activations