© 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. 8536
    Prev
    Next
    INDEX
    Explanations

    words related to planning, organizing, and preparing for different activities or tasks

    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
    51
    +0.14
    0.6%
    591
    +0.13
    0.6%
    447
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.14
    0.06
    724
    +0.13
    0.06
    591
    +0.11
    0.04
    Negative Logits
    ħĭ
    -0.65
    eka
    -0.63
     Continued
    -0.63
    ensis
    -0.63
     Higher
    -0.62
    odan
    -0.61
     Alone
    -0.61
    imaru
    -0.61
    xit
    -0.60
     bidder
    -0.59
    POSITIVE LOGITS
     crammed
    0.90
     nowadays
    0.86
     imaginable
    0.84
     besides
    0.76
     involved
    0.76
    ðŁij
    0.75
     lately
    0.75
     happening
    0.74
     including
    0.73
     vying
    0.72
    Activations Density 0.312%

    No Known Activations