© 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. 8579
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and organizations

    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
    481
    +0.09
    0.4%
    5
    +0.09
    0.4%
    597
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.06
    247
    +0.09
    0.04
    232
    +0.09
    0.04
    Negative Logits
     notch
    -0.80
     disg
    -0.79
     rake
    -0.72
     shade
    -0.72
     flask
    -0.72
     shroud
    -0.71
    inventoryQuantity
    -0.71
     blanket
    -0.70
     anonymity
    -0.70
     fed
    -0.70
    POSITIVE LOGITS
     Association
    1.79
     Associ
    1.59
     Federation
    1.28
     Profession
    1.23
     Society
    1.22
     Council
    1.21
     Owners
    1.17
     Products
    1.17
     Manufact
    1.14
     Industry
    1.13
    Activations Density 0.232%

    No Known Activations