© 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. 16165
    Prev
    Next
    INDEX
    Explanations

    verbs related to legal actions or procedures

    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
    481
    +0.17
    0.8%
    125
    +0.10
    0.5%
    161
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.17
    0.08
    608
    +0.10
    0.08
    557
    +0.10
    0.04
    Negative Logits
    Ö¼
    -0.85
    _-
    -0.77
     didnt
    -0.70
     {*
    -0.68
    ãĥĥãĥī
    -0.62
     slept
    -0.61
     guiActive
    -0.60
     understatement
    -0.60
    fal
    -0.58
     liner
    -0.58
    POSITIVE LOGITS
     respectively
    1.13
     themselves
    0.93
     respective
    0.90
     their
    0.89
     apiece
    0.86
     collectively
    0.75
     jointly
    0.71
     Their
    0.71
     THEIR
    0.71
     together
    0.68
    Activations Density 0.781%

    No Known Activations