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 49152
    5. 8-RES_FS49152-JB
    6. 25585
    Prev
    Next
    INDEX
    Explanations

    terminology related to fighter jets and military aircraft

    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
    78
    +0.10
    0.5%
    435
    +0.10
    0.4%
    115
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.10
    0.02
    343
    +0.10
    0.02
    78
    +0.10
    0.01
    Negative Logits
    estamp
    -0.83
     Sabb
    -0.74
    âĸ¬
    -0.68
    healthy
    -0.68
    hra
    -0.68
    ãĥ´
    -0.67
    properties
    -0.66
    hess
    -0.65
     KDE
    -0.64
    igl
    -0.63
    POSITIVE LOGITS
    bis
    1.01
     aircraft
    0.95
     Intercept
    0.95
     fighter
    0.94
     bomber
    0.91
     squadron
    0.91
     helicopters
    0.89
     cockpit
    0.88
     armoured
    0.87
     Aerospace
    0.86
    Activations Density 0.020%

    No Known Activations