© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare facilities or clinics

    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
    481
    +0.14
    0.7%
    295
    +0.13
    0.6%
    388
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.14
    0.02
    295
    +0.13
    0.02
    114
    +0.12
    0.02
    Negative Logits
    lass
    -0.84
    lasses
    -0.76
     Marketable
    -0.68
    topic
    -0.67
    gest
    -0.66
    lust
    -0.66
    trap
    -0.65
    ulkan
    -0.65
    fall
    -0.65
    loss
    -0.65
    POSITIVE LOGITS
     specializing
    0.90
     clinic
    0.89
    opath
    0.84
     clinics
    0.83
     staffed
    0.82
     attendant
    0.81
     pharmacy
    0.80
     operated
    0.80
     technician
    0.78
     facilities
    0.77
    Activations Density 0.029%

    No Known Activations