© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1477
    Prev
    Next
    INDEX
    Explanations

    time-related terms and durations like months, years, weeks, moments

    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
    564
    +0.13
    0.6%
    71
    +0.11
    0.5%
    82
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.13
    0.05
    82
    +0.11
    0.04
    279
    +0.10
    0.04
    Negative Logits
    emort
    -0.80
    tymology
    -0.79
    ouf
    -0.78
    ahime
    -0.77
    ociate
    -0.77
    aleb
    -0.76
    arton
    -0.75
    ymm
    -0.73
    ells
    -0.72
    dinand
    -0.71
    POSITIVE LOGITS
     thereafter
    1.22
     throughout
    0.85
     until
    0.80
    night
    0.78
     except
    0.73
     regardless
    0.70
     till
    0.68
     imaginable
    0.68
    til
    0.67
     during
    0.67
    Activations Density 0.127%

    No Known Activations