© 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. 7828
    Prev
    Next
    INDEX
    Explanations

    names of countries

    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
    721
    +0.12
    0.5%
    306
    +0.10
    0.5%
    551
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.12
    0.03
    60
    +0.10
    0.03
    551
    +0.10
    0.03
    Negative Logits
     striving
    -0.69
     Confeder
    -0.62
     dishon
    -0.59
     reven
    -0.58
     rehears
    -0.57
    é¾įå¥ij士
    -0.57
     BAL
    -0.57
     honoring
    -0.57
     Ivory
    -0.56
     Architects
    -0.55
    POSITIVE LOGITS
    't
    1.50
    berra
    1.37
    vas
    1.33
    adian
    1.31
    isters
    1.15
    ister
    1.08
    opy
    1.08
    nery
    1.02
    ibal
    0.99
    icum
    0.97
    Activations Density 0.059%

    No Known Activations