© 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. 20331
    Prev
    Next
    INDEX
    Explanations

    medical terms related to drugs and injections

    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
    132
    +0.13
    0.6%
    718
    +0.13
    0.6%
    571
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.13
    0.01
    326
    +0.13
    0.01
    289
    +0.10
    0.01
    Negative Logits
     sear
    -0.73
    ONSORED
    -0.70
     actionGroup
    -0.68
    arded
    -0.65
    ois
    -0.64
    uca
    -0.64
    asted
    -0.63
     Erd
    -0.62
     unsolved
    -0.62
    halla
    -0.61
    POSITIVE LOGITS
    philis
    1.14
    ringe
    1.09
    lv
    0.94
    phthal
    0.92
     sy
    0.88
    bil
    0.85
    racuse
    0.84
    ration
    0.84
    closed
    0.79
    admin
    0.78
    Activations Density 0.033%

    No Known Activations