© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8883
    Prev
    Next
    INDEX
    Explanations

    surnames

    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
    238
    +0.10
    0.5%
    356
    +0.10
    0.4%
    145
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.10
    0.01
    659
    +0.10
    0.01
    57
    +0.10
    0.01
    Negative Logits
    ichick
    -0.93
    enegger
    -0.79
     Reloaded
    -0.77
    DERR
    -0.75
    ELS
    -0.68
    MAP
    -0.64
    yrinth
    -0.64
    VIEW
    -0.63
    INESS
    -0.62
     Tycoon
    -0.62
    POSITIVE LOGITS
    cery
    1.27
    ority
    1.22
    iculture
    0.94
    cer
    0.94
    bet
    0.90
    cha
    0.89
    rell
    0.89
    nery
    0.88
    rha
    0.88
    itic
    0.88
    Activations Density 0.019%

    No Known Activations