© 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. 8112
    Prev
    Next
    INDEX
    Explanations

    comments or discussions related to legal matters

    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
    87
    +0.21
    1.0%
    756
    +0.12
    0.6%
    248
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.21
    -0.03
    8
    +0.12
    0.05
    98
    +0.10
    0.06
    Negative Logits
    quartered
    -0.69
    rote
    -0.66
    Located
    -0.62
     Originally
    -0.59
    itute
    -0.56
    æ©Ł
    -0.56
    atial
    -0.56
    express
    -0.55
    allowed
    -0.54
    ospital
    -0.54
    POSITIVE LOGITS
     someday
    1.29
     tomorrow
    1.23
     next
    1.01
    morrow
    0.99
     future
    0.95
     sooner
    0.92
     2019
    0.91
     2020
    0.90
     soon
    0.88
     hereafter
    0.87
    Activations Density 0.796%

    No Known Activations