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 6144
    5. 8-RES_FS6144-JB
    6. 5381
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases involving custody disputes, partnerships, and pregnancies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    234
    +0.12
    0.6%
    694
    +0.10
    0.5%
    567
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.12
    0.04
    234
    +0.10
    0.06
    516
    +0.10
    0.06
    Negative Logits
    pmwiki
    -1.02
     looting
    -0.92
     alerts
    -0.78
    CVE
    -0.77
     takedown
    -0.76
    ibaba
    -0.74
    eco
    -0.73
     outage
    -0.73
     besie
    -0.72
     Flavoring
    -0.72
    POSITIVE LOGITS
     daughters
    1.36
     unmarried
    1.32
     daughter
    1.32
     married
    1.31
     childbirth
    1.31
     marriage
    1.31
     pregnant
    1.30
     pregnancies
    1.28
    married
    1.28
    marriage
    1.27
    Activations Density 1.469%

    No Known Activations