© 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. 45852
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" or "an."

    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
    36
    +0.18
    0.8%
    218
    +0.15
    0.7%
    393
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.18
    0.04
    218
    +0.15
    0.03
    397
    +0.13
    0.03
    Negative Logits
    andon
    -0.88
    mares
    -0.84
    events
    -0.74
    rences
    -0.73
    bars
    -0.72
    oots
    -0.71
    uez
    -0.71
    EMA
    -0.71
    alties
    -0.70
    osc
    -0.70
    POSITIVE LOGITS
     result
    1.33
     consequence
    1.25
     reminder
    1.21
     footnote
    1.02
     precaution
    1.00
     consolation
    0.99
     testament
    0.97
     refres
    0.97
     workaround
    0.96
     disclaimer
    0.94
    Activations Density 0.030%

    No Known Activations