© 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. 7824
    Prev
    Next
    INDEX
    Explanations

    phrases that pose questions or express doubts

    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
    109
    +0.11
    0.5%
    419
    +0.11
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.11
    0.04
    601
    +0.11
    0.03
    172
    +0.10
    0.03
    Negative Logits
    quer
    -0.68
    hack
    -0.64
    gain
    -0.60
    quin
    -0.59
    ument
    -0.59
    query
    -0.57
    athon
    -0.56
    brid
    -0.55
     Radius
    -0.54
    iy
    -0.54
    POSITIVE LOGITS
     they
    0.85
     THEY
    0.79
    atta
    0.68
    Filename
    0.68
     "[
    0.63
     he
    0.62
     she
    0.61
    they
    0.60
    ="/
    0.60
    ãĢİ
    0.60
    Activations Density 0.187%

    No Known Activations