© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    specific questions or issues within a text

    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
    408
    +0.11
    0.5%
    268
    +0.10
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.11
    0.01
    341
    +0.10
    0.01
    408
    +0.10
    0.02
    Negative Logits
    azon
    -0.82
    unts
    -0.81
    pan
    -0.75
     Citiz
    -0.73
    lez
    -0.73
    ves
    -0.71
    ntil
    -0.69
    lar
    -0.68
    ADRA
    -0.67
    ERAL
    -0.67
    POSITIVE LOGITS
     guiActiveUn
    0.66
    hess
    0.65
     belonged
    0.61
     è£ıè
    0.61
     earlier
    0.60
     posed
    0.59
    oux
    0.58
    代
    0.57
    :(
    0.57
     belong
    0.57
    Activations Density 0.053%

    No Known Activations