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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 43352
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purposes or intentions, particularly those starting with "for."

    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
    362
    +0.15
    0.7%
    507
    +0.09
    0.4%
    245
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.05
    403
    +0.09
    0.03
    755
    +0.09
    0.03
    Negative Logits
    entimes
    -0.79
    zona
    -0.73
    hai
    -0.73
    hews
    -0.73
    sonian
    -0.70
    cz
    -0.70
    forge
    -0.70
    omics
    -0.70
    chenko
    -0.69
    edin
    -0.68
    POSITIVE LOGITS
    gery
    1.04
     sale
    0.98
     upcoming
    0.94
    bidden
    0.92
    geries
    0.91
     each
    0.88
     inclusion
    0.85
     hire
    0.80
     purposes
    0.76
    ked
    0.75
    Activations Density 0.104%

    No Known Activations