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

    Neuronpedia

    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. 9825
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events or periods, specifically focusing on the 17th and 19th centuries

    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
    288
    +0.13
    0.6%
    447
    +0.12
    0.5%
    468
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.13
    0.02
    132
    +0.12
    0.02
    258
    +0.10
    0.02
    Negative Logits
    aturday
    -0.88
    iquid
    -0.86
    hod
    -0.81
    imity
    -0.78
    ECTION
    -0.77
    MAT
    -0.74
    aspx
    -0.73
    uala
    -0.73
    Pack
    -0.71
    uable
    -0.71
    POSITIVE LOGITS
     BCE
    0.92
     onwards
    0.81
     colonial
    0.78
     era
    0.77
     Britons
    0.74
     onward
    0.73
     Britain
    0.72
     British
    0.72
     Europeans
    0.70
     CE
    0.69
    Activations Density 0.040%

    No Known Activations