© 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. 12324
    Prev
    Next
    INDEX
    Explanations

    words related to healthcare policies and legislative measures

    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
    362
    +0.15
    0.7%
    79
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.05
    608
    +0.11
    0.05
    507
    +0.10
    0.04
    Negative Logits
    edin
    -0.95
    bell
    -0.84
    forward
    -0.82
    sonian
    -0.80
    nick
    -0.80
    jet
    -0.73
    é¾
    -0.73
    angelo
    -0.73
    å£
    -0.72
    acci
    -0.71
    POSITIVE LOGITS
    bidden
    1.14
     purposes
    1.00
     starters
    0.91
     minorities
    0.90
     those
    0.89
     individuals
    0.85
     sake
    0.85
    cible
    0.85
     disadvantaged
    0.85
     citizens
    0.83
    Activations Density 0.161%

    No Known Activations