© 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. 15710
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and code snippets

    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
    +0.24
    1.1%
    481
    +0.10
    0.5%
    209
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    731
    +0.24
    0.02
    419
    +0.10
    0.03
    595
    +0.10
    0.02
    Negative Logits
    eele
    -0.78
    trak
    -0.68
     vou
    -0.67
     Palest
    -0.67
    ãĥ©ãĥ³
    -0.63
    etus
    -0.63
    agara
    -0.63
    adem
    -0.62
    oola
    -0.61
    vernment
    -0.60
    POSITIVE LOGITS
    endif
    0.80
     Delete
    0.65
     Default
    0.63
    APTER
    0.62
     Journals
    0.62
    easy
    0.61
     NOTE
    0.61
     furthermore
    0.59
     Tags
    0.59
    else
    0.59
    Activations Density 0.151%

    No Known Activations