© 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. 18794
    Prev
    Next
    INDEX
    Explanations

    phrases related to scheduling and planning

    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
    651
    +0.15
    0.7%
    267
    +0.09
    0.4%
    649
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.15
    0.03
    485
    +0.09
    0.02
    690
    +0.09
    0.01
    Negative Logits
    nai
    -0.74
    tein
    -0.74
    inals
    -0.72
    geoning
    -0.72
    iably
    -0.70
    iants
    -0.70
    ston
    -0.69
    vironment
    -0.68
    iage
    -0.67
    ilee
    -0.67
    POSITIVE LOGITS
     schedules
    1.07
    dule
    1.02
     schedule
    0.95
     Sched
    0.85
     scheduling
    0.85
     sched
    0.82
     TBD
    0.80
     assignments
    0.80
    DAQ
    0.78
     appointments
    0.77
    Activations Density 0.043%

    No Known Activations