© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or official records

    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
    540
    +0.11
    0.5%
    547
    +0.10
    0.5%
    709
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.11
    0.08
    651
    +0.10
    0.06
    274
    +0.10
    0.05
    Negative Logits
    utenberg
    -0.72
    ynchron
    -0.69
    inyl
    -0.67
    ience
    -0.66
    ient
    -0.63
    atism
    -0.62
     Converted
    -0.62
    rogens
    -0.61
    vantage
    -0.61
    planet
    -0.59
    POSITIVE LOGITS
     preceding
    0.75
    notes
    0.71
     acknowled
    0.69
     vicinity
    0.68
     above
    0.68
     roundup
    0.68
     circles
    0.66
     onwards
    0.63
     plaza
    0.63
     booth
    0.63
    Activations Density 0.349%

    No Known Activations