© 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 49152
    9. 8-RES_FS49152-JB
    11. 25786
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    109
    +0.09
    0.4%
    447
    +0.09
    0.4%
    544
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.09
    0.03
    536
    +0.09
    0.03
    275
    +0.09
    0.02
    Negative Logits
    inary
    -0.71
    rats
    -0.64
    nerg
    -0.62
     caliber
    -0.62
    atible
    -0.62
    Justice
    -0.61
    OTUS
    -0.61
     totality
    -0.59
    swick
    -0.59
     Organization
    -0.57
    POSITIVE LOGITS
    hiba
    0.81
    ansky
    0.80
    ynthesis
    0.77
    ometimes
    0.75
    advertisement
    0.74
    omething
    0.71
    kowski
    0.68
     confidently
    0.67
     rhet
    0.67
    é¾
    0.67
    Activations Density 0.043%

    No Known Activations