© 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. 478
    Prev
    Next
    INDEX
    Explanations

    phrases related to regret or missed opportunities

    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
    699
    +0.14
    0.6%
    154
    +0.10
    0.5%
    479
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.04
    699
    +0.10
    0.03
    55
    +0.10
    0.04
    Negative Logits
     Deb
    -0.64
    adj
    -0.62
     usually
    -0.62
    verend
    -0.61
     currently
    -0.59
     Dj
    -0.59
     now
    -0.58
    inki
    -0.57
    tymology
    -0.56
     presently
    -0.55
    POSITIVE LOGITS
     sooner
    1.02
    MpServer
    0.69
     differently
    0.68
     unthinkable
    0.67
    Ire
    0.66
     wiser
    0.65
     millenn
    0.64
    iscons
    0.64
    LOCK
    0.63
    ypes
    0.63
    Activations Density 0.233%

    No Known Activations