© 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. 12036
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and societal issues, including justice, security, policies, regulations, and enforcement

    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
    480
    +0.51
    2.6%
    266
    +0.11
    0.6%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.01
    266
    +0.11
    0.08
    288
    +0.10
    0.10
    Negative Logits
    $.
    -0.79
    *.
    -0.75
    !.
    -0.70
    `.
    -0.69
    thia
    -0.68
    arettes
    -0.67
    +.
    -0.64
    .$
    -0.64
    ecause
    -0.64
    Ú
    -0.64
    POSITIVE LOGITS
     trio
    0.72
     portion
    0.70
     duo
    0.69
    iest
    0.66
     version
    0.64
     analogy
    0.64
     question
    0.62
     team
    0.61
     approach
    0.60
     operator
    0.60
    Activations Density 0.830%

    No Known Activations