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. 1212
    Prev
    Next
    INDEX
    Explanations

    information related to box office numbers and movie performance

    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
    7
    +0.10
    0.4%
    36
    +0.09
    0.4%
    552
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.10
    0.04
    422
    +0.09
    0.03
    596
    +0.09
    0.03
    Negative Logits
    CHAT
    -0.86
     [&
    -0.72
     schematic
    -0.72
     counsel
    -0.71
    obyl
    -0.70
    plain
    -0.70
     tink
    -0.68
     sche
    -0.68
     biome
    -0.68
     sten
    -0.66
    POSITIVE LOGITS
     viewership
    1.15
     theaters
    1.05
     debut
    0.97
     domestically
    0.95
     sequels
    0.94
     blockbuster
    0.88
     audiences
    0.88
    advertising
    0.87
     Paramount
    0.86
     premiere
    0.85
    Activations Density 0.392%

    No Known Activations