© 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. 332
    Prev
    Next
    INDEX
    Explanations

    phrases related to time that indicate sequential events

    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
    267
    +0.12
    0.5%
    237
    +0.09
    0.4%
    582
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.12
    0.04
    582
    +0.09
    0.03
    168
    +0.09
    0.03
    Negative Logits
    ties
    -0.71
    leading
    -0.63
    toe
    -0.63
    ded
    -0.63
    ische
    -0.63
    cv
    -0.62
    Latin
    -0.60
    md
    -0.60
    ãĥĸ
    -0.59
    ga
    -0.58
    POSITIVE LOGITS
    adays
    0.88
     secondly
    0.81
     comes
    0.79
     suddenly
    0.78
     proceeded
    0.78
     came
    0.74
     Comes
    0.72
    ulhu
    0.71
    Ļ½
    0.71
     abruptly
    0.70
    Activations Density 0.064%

    No Known Activations