© 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. 8894
    Prev
    Next
    INDEX
    Explanations

    references to legal and government entities and actions within documents

    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
    87
    +0.32
    1.7%
    373
    +0.15
    0.8%
    470
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.32
    -0.02
    470
    +0.15
    0.04
    224
    +0.09
    0.06
    Negative Logits
     whilst
    -0.84
    Firstly
    -0.74
     civilisation
    -0.74
    !".
    -0.73
    ãĥİ
    -0.71
    ãĢİ
    -0.70
     fucking
    -0.70
     realise
    -0.70
    ".[
    -0.69
     util
    -0.69
    POSITIVE LOGITS
     spokeswoman
    1.06
     spokesman
    0.95
     Grassley
    0.89
     attorneys
    0.89
     attorney
    0.88
     Judicial
    0.79
     ACLU
    0.73
     spokesperson
    0.70
     testified
    0.70
     Oversight
    0.70
    Activations Density 0.966%

    No Known Activations