© 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 12288
    9. 8-RES_FS12288-JB
    11. 10317
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "keep an eye on" or "keep an eye out for."

    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
    747
    +0.12
    0.5%
    125
    +0.11
    0.5%
    272
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.12
    0.03
    435
    +0.11
    0.03
    747
    +0.10
    0.02
    Negative Logits
    inished
    -0.79
     satisfaction
    -0.66
    cible
    -0.65
    inant
    -0.63
     apologized
    -0.63
    yrics
    -0.61
    lyn
    -0.61
     rendition
    -0.59
    enei
    -0.59
    hement
    -0.59
    POSITIVE LOGITS
     lest
    0.99
     closely
    0.81
    atches
    0.81
    tower
    0.73
    SEE
    0.69
     Monitor
    0.69
    wl
    0.68
     Yen
    0.67
     ahead
    0.67
     developments
    0.66
    Activations Density 0.175%

    No Known Activations