© 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. 15901
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of places, individuals, or entities

    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
    +0.23
    1.2%
    481
    +0.23
    1.2%
    367
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.23
    0.08
    232
    +0.23
    0.07
    288
    +0.12
    0.09
    Negative Logits
     UNCLASSIFIED
    -0.79
    anwhile
    -0.75
    enegger
    -0.71
     [*
    -0.68
    }.
    -0.65
    )).
    -0.64
    jri
    -0.63
     afterward
    -0.63
    âķIJ
    -0.63
     thereafter
    -0.63
    POSITIVE LOGITS
     Brewing
    0.72
     âĢº
    0.65
    Coin
    0.62
    coin
    0.61
    reetings
    0.59
    Arcade
    0.59
    Brew
    0.59
     Beer
    0.58
    Game
    0.57
    ÂŃ
    0.56
    Activations Density 0.570%

    No Known Activations