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. 445
    Prev
    Next
    INDEX
    Explanations

    phrases related to current events or news stories

    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
    102
    +0.12
    0.5%
    66
    +0.12
    0.5%
    230
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.11
    190
    +0.12
    0.10
    422
    +0.12
    0.07
    Negative Logits
     Tags
    -0.73
     Grants
    -0.73
     GEAR
    -0.69
    ĺħ
    -0.68
     Dreams
    -0.65
     Taxes
    -0.64
     Contracts
    -0.63
     Jackets
    -0.63
    culosis
    -0.63
     Travels
    -0.63
    POSITIVE LOGITS
    famous
    0.88
     volatile
    0.86
     diverse
    0.85
     expansive
    0.84
     eclectic
    0.83
     sophisticated
    0.83
    interesting
    0.82
     disparate
    0.82
     unorthodox
    0.81
     pristine
    0.81
    Activations Density 1.104%

    No Known Activations