© 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. 17474
    Prev
    Next
    INDEX
    Explanations

    comparisons between different levels or instances of importance or value

    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
    348
    +0.11
    0.5%
    684
    +0.10
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.11
    0.03
    393
    +0.10
    0.04
    692
    +0.10
    0.03
    Negative Logits
    psey
    -0.64
    Reviewed
    -0.62
    atoon
    -0.58
     wondered
    -0.57
    âĹ¼
    -0.56
    awar
    -0.55
    may
    -0.55
    imar
    -0.55
    aston
    -0.55
     Wouldn
    -0.55
    POSITIVE LOGITS
     actual
    0.87
     necessarily
    0.84
     mere
    0.76
     substance
    0.74
     merely
    0.74
     outright
    0.69
    DATA
    0.66
    ogle
    0.65
     anything
    0.63
     quantity
    0.60
    Activations Density 0.212%

    No Known Activations