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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1647
    Prev
    Next
    INDEX
    Explanations

    comparisons and differences between different entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    276
    +0.10
    0.5%
    679
    +0.10
    0.5%
    438
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.10
    0.04
    329
    +0.10
    0.04
    131
    +0.10
    0.03
    Negative Logits
    authorized
    -0.74
    Bay
    -0.64
    ãĥİ
    -0.61
    arse
    -0.60
    achment
    -0.58
    uler
    -0.58
    bean
    -0.58
    lear
    -0.57
    utters
    -0.57
    noon
    -0.57
    POSITIVE LOGITS
     favorably
    0.99
     apples
    0.86
     Compare
    0.81
     favour
    0.77
    isons
    0.76
     between
    0.76
    xual
    0.75
     sexes
    0.73
     compare
    0.72
     comparison
    0.72
    Activations Density 0.464%

    No Known Activations