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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21191
    Prev
    Next
    INDEX
    Explanations

    words related to rules or decisions being made

    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
    708
    +0.11
    0.5%
    756
    +0.11
    0.5%
    468
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.11
    0.02
    611
    +0.11
    0.02
    756
    +0.10
    0.00
    Negative Logits
    issance
    -0.85
    ufact
    -0.78
    akra
    -0.78
    ription
    -0.77
    illin
    -0.73
     Pastebin
    -0.70
    isable
    -0.68
    velength
    -0.66
    Newsletter
    -0.66
    ickr
    -0.65
    POSITIVE LOGITS
    phas
    0.82
     differently
    0.82
     definitively
    0.77
     against
    0.76
     out
    0.72
     decisively
    0.71
     unfit
    0.70
    lessly
    0.66
    tto
    0.65
    maker
    0.65
    Activations Density 0.019%

    No Known Activations