© 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. 8554
    Prev
    Next
    INDEX
    Explanations

    dates and specific descriptions of legal actions

    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
    480
    +0.47
    2.4%
    87
    +0.17
    0.9%
    447
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.47
    0.03
    266
    +0.17
    0.10
    376
    +0.17
    0.03
    Negative Logits
    ãĤ´ãĥ³
    -0.74
     respectively
    -0.61
    surprisingly
    -0.58
    anwhile
    -0.56
    xtap
    -0.54
    etheless
    -0.53
    ometimes
    -0.53
     "_
    -0.51
    essage
    -0.50
     "#
    -0.48
    POSITIVE LOGITS
    ,'"
    1.42
    ,"
    1.35
    "—
    1.35
    %"
    1.34
     âĢ¦"
    1.32
     ..."
    1.28
    .")
    1.27
    ),"
    1.27
    ")
    1.26
    )",
    1.24
    Activations Density 1.134%

    No Known Activations