© 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. 8083
    Prev
    Next
    INDEX
    Explanations

    words related to geographical and physical locations or objects, specifically with a focus on "poles" like geographic poles or dance poles

    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
    187
    +0.11
    0.5%
    666
    +0.10
    0.5%
    710
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.01
    326
    +0.10
    0.01
    666
    +0.10
    0.01
    Negative Logits
    iencies
    -0.86
    æĸ¹
    -0.84
    enegger
    -0.83
    lycer
    -0.82
    ergy
    -0.79
    Export
    -0.77
    ONSORED
    -0.76
    ebook
    -0.76
    Interstitial
    -0.75
    iasco
    -0.75
    POSITIVE LOGITS
     pole
    1.26
     poles
    1.02
    pole
    0.99
     Pole
    0.98
    mic
    0.97
     Poles
    0.77
    isphere
    0.76
     maiden
    0.74
    axe
    0.71
    ward
    0.70
    Activations Density 0.024%

    No Known Activations