© 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 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. 17389
    Prev
    Next
    INDEX
    Explanations

    information related to legal rights and publications

    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
    373
    +0.12
    0.6%
    101
    +0.11
    0.5%
    767
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.03
    530
    +0.11
    0.02
    373
    +0.10
    -0.01
    Negative Logits
    burgh
    -0.65
    hell
    -0.61
     satisfactory
    -0.59
    tle
    -0.59
     convinc
    -0.59
    han
    -0.59
    milo
    -0.58
     boo
    -0.57
    uates
    -0.57
     dracon
    -0.57
    POSITIVE LOGITS
     reprint
    0.79
    verning
    0.78
    license
    0.75
     Attribution
    0.74
    Copyright
    0.74
     Reserved
    0.72
     Terms
    0.71
    usha
    0.71
     copyright
    0.69
     restraint
    0.66
    Activations Density 0.074%

    No Known Activations