© 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. 5627
    Prev
    Next
    INDEX
    Explanations

    information related to geographic regions or countries, particularly in the context of statistics or developments

    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
    469
    +0.12
    0.5%
    648
    +0.11
    0.5%
    552
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.12
    0.03
    488
    +0.11
    0.04
    296
    +0.10
    0.04
    Negative Logits
    ullah
    -0.69
    bart
    -0.67
    imo
    -0.63
    oring
    -0.63
    #$
    -0.62
    optional
    -0.61
    æĦ
    -0.60
    bol
    -0.59
    mint
    -0.58
    iol
    -0.58
    POSITIVE LOGITS
     previous
    1.21
     prior
    1.00
     2007
    0.90
     predecessor
    0.89
     2015
    0.88
     preceding
    0.88
     earlier
    0.88
     last
    0.87
     2009
    0.87
     2011
    0.86
    Activations Density 0.157%

    No Known Activations