© 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. 8524
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard or diligently on a task

    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
    665
    +0.14
    0.7%
    447
    +0.12
    0.6%
    333
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.07
    718
    +0.12
    0.06
    608
    +0.12
    0.06
    Negative Logits
     Used
    -0.68
     Spaces
    -0.65
     curs
    -0.64
    lesi
    -0.63
     Floating
    -0.63
    quickShipAvailable
    -0.63
     Cust
    -0.61
     Klu
    -0.59
     slang
    -0.59
    pict
    -0.58
    POSITIVE LOGITS
     ensure
    1.39
     minimize
    1.33
     improve
    1.32
     optimize
    1.25
     maximize
    1.24
     promote
    1.22
     achieve
    1.21
     educate
    1.18
     conserve
    1.18
     integrate
    1.17
    Activations Density 0.159%

    No Known Activations