© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    terms related to the Environmental Protection Agency (EPA) and its activities

    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
    447
    +0.13
    0.6%
    644
    +0.11
    0.5%
    742
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.13
    0.01
    461
    +0.11
    0.01
    146
    +0.10
    0.01
    Negative Logits
    orne
    -0.80
    acters
    -0.75
     Dracula
    -0.70
     Kinn
    -0.69
    itars
    -0.66
    eners
    -0.66
    akia
    -0.65
    ching
    -0.65
    aji
    -0.64
    hood
    -0.64
    POSITIVE LOGITS
    EPA
    1.00
     Administrator
    1.00
    sburg
    0.88
     administrator
    0.85
     Fisheries
    0.77
     EPA
    0.76
    TN
    0.75
    è¦ļéĨĴ
    0.75
     inspector
    0.75
    BAT
    0.72
    Activations Density 0.017%

    No Known Activations