© 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. 20373
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "no more" is used in a context that signifies a change or termination of certain actions or conditions

    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
    726
    +0.11
    0.5%
    754
    +0.10
    0.5%
    389
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.11
    0.02
    13
    +0.10
    0.02
    389
    +0.09
    0.02
    Negative Logits
    yip
    -0.74
    hare
    -0.72
    irez
    -0.72
    enger
    -0.70
    ĪĴ
    -0.70
    issance
    -0.69
    pherd
    -0.69
    =-=-
    -0.68
    cius
    -0.68
    ĺħ
    -0.68
    POSITIVE LOGITS
     than
    0.94
     nor
    0.80
     ado
    0.78
     whatsoever
    0.78
    Fake
    0.73
     excuses
    0.73
     usable
    0.65
     pancakes
    0.65
     surprises
    0.63
     Than
    0.62
    Activations Density 0.034%

    No Known Activations