© 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. 8637
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming commands related to aggregation or modification operations

    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
    712
    +0.11
    0.5%
    748
    +0.10
    0.5%
    29
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.00
    586
    +0.10
    0.01
    277
    +0.10
    0.01
    Negative Logits
    iple
    -0.86
    irk
    -0.78
    ortal
    -0.77
    anmar
    -0.76
    hum
    -0.74
    yright
    -0.74
    stein
    -0.73
    olls
    -0.73
    resident
    -0.72
    alach
    -0.72
    POSITIVE LOGITS
     {"
    1.01
     ({
    0.92
     println
    0.90
     {}
    0.86
     [];
    0.80
     {:
    0.79
     nil
    0.78
     undefined
    0.74
     None
    0.73
     {
    0.73
    Activations Density 0.004%

    No Known Activations