© 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. 18423
    Prev
    Next
    INDEX
    Explanations

    instances of laws, regulations, and government-related terms and actions

    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
    494
    +0.10
    0.5%
    445
    +0.09
    0.4%
    1
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.10
    0.03
    449
    +0.09
    0.03
    239
    +0.09
    0.03
    Negative Logits
    eteen
    -0.77
    stones
    -0.72
     Cruel
    -0.69
    '';
    -0.66
     âĢİ
    -0.65
    hart
    -0.65
    itiz
    -0.65
    igators
    -0.64
    ":-
    -0.63
    bats
    -0.63
    POSITIVE LOGITS
     rightfully
    0.81
     rightly
    0.77
     unsuccessfully
    0.75
     indeed
    0.72
     preferably
    0.72
     tolerated
    0.71
     admittedly
    0.69
    nown
    0.69
     albeit
    0.67
     optionally
    0.67
    Activations Density 0.099%

    No Known Activations