© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    news articles reporting on tragic incidents or accidents

    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
    373
    +0.25
    1.2%
    640
    +0.14
    0.6%
    145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.25
    -0.00
    361
    +0.14
    0.03
    640
    +0.11
    0.03
    Negative Logits
    ichick
    -0.95
    ãĥ¼ãĥĨãĤ£
    -0.78
    ãĥ¼ãĥĨ
    -0.70
    ãĤ©
    -0.66
    ²
    -0.66
     Alchemy
    -0.64
    ãĤ¡
    -0.64
     wow
    -0.64
    ij士
    -0.63
    rer
    -0.63
    POSITIVE LOGITS
    Scientists
    0.87
    Authorities
    0.81
    Pak
    0.78
    Earlier
    0.75
    Officials
    0.73
    Updated
    0.73
     Britons
    0.73
    Thousands
    0.72
    Britain
    0.71
    Sorry
    0.71
    Activations Density 0.034%

    No Known Activations