© 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 12288
    9. 8-RES_FS12288-JB
    11. 1653
    Prev
    Next
    INDEX
    Explanations

    concepts related to evidence, estimation, and pointing towards facts or conclusions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    702
    +0.10
    0.5%
    430
    +0.10
    0.4%
    39
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.10
    0.06
    407
    +0.10
    0.04
    679
    +0.09
    0.07
    Negative Logits
     Shutterstock
    -0.77
     Gazette
    -0.73
    iliary
    -0.71
    ufact
    -0.66
     Pastebin
    -0.65
    ãĥĩ
    -0.64
    ãĥ¬
    -0.64
    ivic
    -0.63
    utterstock
    -0.62
    bestos
    -0.61
    POSITIVE LOGITS
     probabilities
    0.88
     doom
    0.82
     unequivocally
    0.78
     probability
    0.77
     definitively
    0.73
     positives
    0.72
     favoring
    0.72
     consensus
    0.71
     conclusive
    0.71
    phas
    0.71
    Activations Density 0.692%

    No Known Activations