© 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. 18747
    Prev
    Next
    INDEX
    Explanations

    information related to healthcare policies and programs

    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
    288
    +0.14
    0.7%
    762
    +0.11
    0.5%
    172
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.14
    0.03
    688
    +0.11
    0.03
    482
    +0.10
    0.03
    Negative Logits
     Helpful
    -0.82
     Reloaded
    -0.81
     Duo
    -0.78
    toe
    -0.77
    anism
    -0.72
    xual
    -0.71
    urat
    -0.70
     Darkness
    -0.70
    yip
    -0.69
    arget
    -0.69
    POSITIVE LOGITS
     care
    1.37
    care
    1.31
     Care
    1.19
     insurance
    1.14
    Care
    1.12
     insurer
    0.98
     insurers
    0.97
     savings
    0.91
    span
    0.90
    amacare
    0.86
    Activations Density 0.029%

    No Known Activations