© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19384
    Prev
    Next
    INDEX
    Explanations

    phrases related to cell regeneration and tissue engineering

    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
    99
    +0.12
    0.5%
    537
    +0.11
    0.5%
    395
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.03
    516
    +0.11
    0.02
    99
    +0.11
    0.02
    Negative Logits
    soDeliveryDate
    -0.73
    ebin
    -0.73
    ãĤª
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.72
    emark
    -0.72
    quickShipAvailable
    -0.72
    essee
    -0.70
    ãĥ¼ãĥ³
    -0.70
    awaru
    -0.70
    ãĥī
    -0.69
    POSITIVE LOGITS
     cells
    1.13
     membranes
    1.09
     Cells
    0.95
     membrane
    0.93
     transpl
    0.90
     mitochond
    0.89
    cells
    0.89
     cell
    0.88
     biologists
    0.88
     harvested
    0.87
    Activations Density 0.027%

    No Known Activations