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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1668
    Prev
    Next
    INDEX
    Explanations

    the word "probably" in the text

    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
    247
    +0.10
    0.4%
    583
    +0.09
    0.4%
    760
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.10
    0.03
    8
    +0.09
    0.03
    583
    +0.09
    0.03
    Negative Logits
    iya
    -0.83
    issy
    -0.77
    elight
    -0.74
    ible
    -0.71
    vers
    -0.71
    osi
    -0.70
    irl
    -0.69
    uctor
    -0.69
    lete
    -0.69
    aeus
    -0.68
    POSITIVE LOGITS
     overest
    0.85
     misunder
    0.83
     underestimate
    0.80
     underest
    0.80
     someday
    0.79
     won
    0.77
     exagger
    0.74
     underestimated
    0.74
     outnumbered
    0.73
     subconscious
    0.71
    Activations Density 0.049%

    No Known Activations