© 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. 9430
    Prev
    Next
    INDEX
    Explanations

    references to holidays and special occasions

    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
    141
    +0.11
    0.5%
    306
    +0.10
    0.5%
    598
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.11
    0.02
    141
    +0.10
    0.02
    651
    +0.10
    0.02
    Negative Logits
    ioch
    -0.75
    ioned
    -0.75
    lucent
    -0.74
    umblr
    -0.72
    obi
    -0.68
    developed
    -0.67
    nih
    -0.67
    apsed
    -0.65
    æ©Ł
    -0.63
    english
    -0.63
    POSITIVE LOGITS
     Eve
    1.20
     eve
    1.07
    iversary
    1.03
     festivities
    0.96
     Celebration
    0.92
     anniversary
    0.89
     2017
    0.82
     holidays
    0.82
     celebrations
    0.81
     celebration
    0.81
    Activations Density 0.052%

    No Known Activations