© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37251
    Prev
    Next
    INDEX
    Explanations

    references to trailers of movies or shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    447
    +0.14
    0.6%
    288
    +0.12
    0.6%
    516
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.14
    0.01
    326
    +0.12
    0.01
    161
    +0.11
    0.01
    Negative Logits
    theless
    -0.89
    urrency
    -0.79
    iott
    -0.77
    gans
    -0.76
    Ĭ±
    -0.74
    ternity
    -0.71
    ¬¼
    -0.67
    urrencies
    -0.67
    currency
    -0.67
    omez
    -0.67
    POSITIVE LOGITS
     trailer
    1.14
     Trailer
    0.91
     trailers
    0.90
    park
    0.75
     hitch
    0.74
    film
    0.72
     projector
    0.71
     footage
    0.70
     filmed
    0.70
     teaser
    0.70
    Activations Density 0.009%

    No Known Activations