© 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. 11990
    Prev
    Next
    INDEX
    Explanations

    violent-related words and phrases

    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
    314
    +0.14
    0.7%
    371
    +0.12
    0.6%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.14
    0.02
    314
    +0.12
    0.01
    366
    +0.10
    0.02
    Negative Logits
    ÄŁ
    -0.62
     guesses
    -0.61
     Tsukuyomi
    -0.59
    edin
    -0.59
     afar
    -0.57
     Paula
    -0.57
     Mb
    -0.56
    ij士
    -0.55
    omething
    -0.54
    vous
    -0.54
    POSITIVE LOGITS
    rice
    1.03
    hemat
    1.03
    hetically
    0.98
    terson
    0.98
    abase
    0.98
    hens
    0.95
    rix
    0.93
    ric
    0.93
    itudes
    0.93
    roph
    0.92
    Activations Density 0.032%

    No Known Activations