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 24576
    5. 8-RES_FS24576-JB
    6. 21538
    Prev
    Next
    INDEX
    Explanations

    references to box office performance in the entertainment industry

    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
    174
    +0.12
    0.5%
    447
    +0.10
    0.5%
    442
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.12
    0.02
    288
    +0.10
    0.03
    151
    +0.10
    0.02
    Negative Logits
    icum
    -0.74
    sonian
    -0.71
     Flask
    -0.70
    onomous
    -0.68
    ¬¼
    -0.68
     Hast
    -0.68
     Oss
    -0.67
    urion
    -0.66
    ĪĴ
    -0.66
    meal
    -0.65
    POSITIVE LOGITS
     domestically
    0.96
    ivals
    0.92
     theaters
    0.89
    genre
    0.83
    atform
    0.83
     gross
    0.80
    ovies
    0.79
     sequels
    0.79
     viewership
    0.79
     receipts
    0.78
    Activations Density 0.086%

    No Known Activations