© 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. 2222
    Prev
    Next
    INDEX
    Explanations

    functions and programming terms related to templates and classes

    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
    586
    +0.11
    0.5%
    80
    +0.10
    0.5%
    405
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    18
    +0.11
    0.05
    314
    +0.10
    -0.00
    659
    +0.10
    0.04
    Negative Logits
    ²¾
    -0.65
     bumper
    -0.62
     Proper
    -0.61
    enko
    -0.60
     destro
    -0.59
    kill
    -0.59
    inctions
    -0.58
    vantage
    -0.57
     experien
    -0.56
    yk
    -0.56
    POSITIVE LOGITS
    actionDate
    0.77
    ItemThumbnailImage
    0.69
    LP
    0.68
    dated
    0.63
     1889
    0.62
    ãĥ¥
    0.60
    cerpt
    0.60
     Balt
    0.59
    )'
    0.59
     TBA
    0.58
    Activations Density 0.307%

    No Known Activations