© 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 EvalsExportsAPI 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. 12720
    Prev
    Next
    INDEX
    Explanations

    expressions related to opinions or beliefs

    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
    447
    +0.13
    0.6%
    609
    +0.12
    0.6%
    529
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.13
    0.04
    529
    +0.12
    0.03
    643
    +0.12
    0.02
    Negative Logits
    orage
    -0.78
     Stephenson
    -0.70
    kie
    -0.68
    inav
    -0.66
    forest
    -0.66
    ev
    -0.66
    ansas
    -0.64
    lins
    -0.62
    ugar
    -0.62
    Reading
    -0.62
    POSITIVE LOGITS
    forth
    0.95
    pmwiki
    0.91
     hesitate
    0.71
     unus
    0.70
     resorted
    0.68
     advis
    0.65
     nickname
    0.64
     often
    0.64
     frequently
    0.64
     instinctively
    0.63
    Activations Density 0.322%

    No Known Activations