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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18921
    Prev
    Next
    INDEX
    Explanations

    words related to economic issues, job availability, and energy sources

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    756
    +0.23
    1.2%
    87
    +0.20
    1.0%
    373
    +0.16
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.23
    -0.00
    570
    +0.20
    0.02
    67
    +0.16
    0.06
    Negative Logits
     Investigator
    -0.79
    canon
    -0.77
     Autism
    -0.70
    Trigger
    -0.70
     Canaver
    -0.66
     Hitchcock
    -0.63
     Creep
    -0.62
     Anonymous
    -0.62
     Shooter
    -0.61
    editor
    -0.61
    POSITIVE LOGITS
     commodities
    1.11
     commodity
    1.00
     goods
    0.99
     workforce
    0.97
     markets
    0.96
     economies
    0.95
     factories
    0.94
     industries
    0.93
     exports
    0.90
     economically
    0.90
    Activations Density 0.917%

    No Known Activations