© 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 12288
    9. 8-RES_FS12288-JB
    11. 10411
    Prev
    Next
    INDEX
    Explanations

    news articles about various incidents and events

    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
    640
    +0.23
    1.1%
    160
    +0.14
    0.7%
    314
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.23
    0.10
    160
    +0.14
    0.10
    442
    +0.14
    0.08
    Negative Logits
     sucker
    -0.75
     branches
    -0.74
     altern
    -0.73
     synerg
    -0.72
     luck
    -0.70
     scales
    -0.69
     additionally
    -0.69
     ba
    -0.68
     claws
    -0.68
     aggreg
    -0.67
    POSITIVE LOGITS
    Updated
    1.67
    Published
    1.53
    Posted
    1.52
    hello
    1.37
    Enlarge
    1.35
    Guest
    1.34
    TOR
    1.32
    WASHINGTON
    1.29
    By
    1.27
    SAN
    1.27
    Activations Density 0.294%

    No Known Activations