© 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. 8008
    Prev
    Next
    INDEX
    Explanations

    statistics or numbers related to casualties or incidents

    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
    214
    +0.10
    0.5%
    687
    +0.10
    0.5%
    498
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.10
    0.03
    687
    +0.10
    0.03
    214
    +0.10
    0.03
    Negative Logits
    taboola
    -0.77
    tions
    -0.69
    ãĤ¿
    -0.62
    SourceFile
    -0.60
    axter
    -0.60
    onomic
    -0.60
    gars
    -0.59
    ohydrate
    -0.58
     messenger
    -0.58
    kai
    -0.58
    POSITIVE LOGITS
     eight
    0.79
     nine
    0.78
     six
    0.77
    eight
    0.76
     four
    0.75
     five
    0.75
     seven
    0.74
    six
    0.74
     129
    0.73
     three
    0.73
    Activations Density 0.024%

    No Known Activations