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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 2681
    Prev
    Next
    INDEX
    Explanations

    references to the "Final Fantasy" game series

    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
    556
    +0.13
    0.6%
    319
    +0.10
    0.4%
    359
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.13
    0.04
    359
    +0.10
    0.02
    384
    +0.09
    0.02
    Negative Logits
    uckland
    -0.93
    elong
    -0.82
    bush
    -0.79
    miss
    -0.76
    inges
    -0.71
    upper
    -0.71
    ifle
    -0.71
    jen
    -0.70
    mand
    -0.69
     cyn
    -0.69
    POSITIVE LOGITS
     XIII
    1.01
     Chronicles
    0.99
     Origins
    0.98
     Generations
    0.97
    âĦ¢:
    0.96
     Awakening
    0.95
     III
    0.95
     VII
    0.94
     XIV
    0.94
     XI
    0.93
    Activations Density 0.058%

    No Known Activations