© 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. 19860
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal relationships and emotional challenges

    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
    447
    +0.26
    1.3%
    570
    +0.10
    0.5%
    617
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.26
    0.05
    8
    +0.10
    0.06
    570
    +0.09
    0.01
    Negative Logits
     Released
    -0.73
    Synopsis
    -0.63
     Shroud
    -0.61
     Adolf
    -0.59
     Published
    -0.56
     proclaimed
    -0.55
     preceding
    -0.54
     Various
    -0.54
     Prix
    -0.54
     Whilst
    -0.54
    POSITIVE LOGITS
    .""
    0.79
     incent
    0.78
    ?"
    0.78
    .''
    0.76
    entimes
    0.76
     [
    0.75
    [/
    0.73
     ..."
    0.73
    .,"
    0.72
    ,''
    0.72
    Activations Density 0.958%

    No Known Activations