© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17254
    Prev
    Next
    INDEX
    Explanations

    descriptions related to cars and driving, along with task-related phrases

    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
    +0.25
    1.2%
    283
    +0.10
    0.5%
    683
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.25
    0.00
    570
    +0.10
    0.03
    283
    +0.09
    0.03
    Negative Logits
     Patreon
    -0.87
     Charity
    -0.68
     Journalism
    -0.64
     theolog
    -0.61
     Eth
    -0.60
     Canaver
    -0.59
     MacArthur
    -0.58
     pastors
    -0.58
     Luxem
    -0.58
     abolition
    -0.58
    POSITIVE LOGITS
    )).
    0.80
    uggage
    0.73
    iped
    0.72
    entary
    0.72
     interact
    0.71
     safely
    0.71
    Interstitial
    0.69
     gaze
    0.68
     wearer
    0.68
     nearby
    0.68
    Activations Density 0.908%

    No Known Activations