© 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 EvalsExportsinterp-engineNEWAPI 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. 4696
    Prev
    Next
    INDEX
    Explanations

    words related to chiropractors

    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
    235
    +0.12
    0.5%
    62
    +0.10
    0.4%
    190
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.04
    235
    +0.10
    0.04
    575
    +0.09
    0.03
    Negative Logits
     Strongh
    -0.85
    lust
    -0.76
     Skies
    -0.73
     Stronghold
    -0.71
    pload
    -0.69
    gered
    -0.67
    wagon
    -0.67
    quote
    -0.67
    ontent
    -0.66
    âĸ¬
    -0.66
    POSITIVE LOGITS
     physician
    1.33
     doctor
    1.32
     practitioner
    1.28
     doctors
    1.27
     surgeon
    1.26
     physicians
    1.26
     medicine
    1.25
     Surgery
    1.24
     patients
    1.22
     pediatric
    1.22
    Activations Density 0.126%

    No Known Activations