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. 1426
    Prev
    Next
    INDEX
    Explanations

    information related to government policies, trade relations, and regulations

    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
    447
    +0.19
    0.9%
    481
    +0.18
    0.8%
    146
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.23
    575
    +0.18
    0.20
    481
    +0.10
    0.18
    Negative Logits
    ussian
    -0.67
    lopp
    -0.64
    awks
    -0.64
     pestic
    -0.59
    erd
    -0.58
     charm
    -0.58
     Hawks
    -0.57
     actionGroup
    -0.56
    keyes
    -0.56
    autions
    -0.55
    POSITIVE LOGITS
    .''.
    0.90
     during
    0.83
     arising
    0.83
     amid
    0.81
    âĢİ
    0.81
     pursuant
    0.79
     abroad
    0.78
    .
    0.76
     occurring
    0.74
     irrespective
    0.73
    Activations Density 3.497%

    No Known Activations