© 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 24576
    9. 8-RES_FS24576-JB
    11. 24108
    Prev
    Next
    INDEX
    Explanations

    references to the concept of patience

    oai_token-act-pair · gpt-4o-miniTriggered 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
    255
    +0.14
    0.6%
    157
    +0.09
    0.4%
    238
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.14
    0.01
    271
    +0.09
    0.01
    312
    +0.09
    0.01
    Negative Logits
    ramid
    -1.18
    tein
    -0.98
    aucus
    -0.87
    opoulos
    -0.77
    inates
    -0.75
    ura
    -0.75
    enes
    -0.75
    unin
    -0.74
    ortium
    -0.74
    ensen
    -0.74
    POSITIVE LOGITS
     patience
    1.18
     patiently
    1.09
     persever
    0.96
     impatient
    0.83
     pige
    0.82
     impat
    0.77
     endurance
    0.72
     waiting
    0.72
     Waiting
    0.70
     delays
    0.68
    Activations Density 0.027%

    No Known Activations