© 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. 20519
    Prev
    Next
    INDEX
    Explanations

    the letter "s" at the beginning or within words

    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
    480
    +0.26
    1.2%
    447
    +0.19
    0.9%
    87
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    520
    +0.26
    0.02
    176
    +0.19
    0.02
    464
    +0.14
    0.02
    Negative Logits
     behavi
    -0.69
    ãĥ¼ãĥĨ
    -0.69
     thous
    -0.66
     Vaugh
    -0.61
     conditions
    -0.61
     destro
    -0.59
     procedures
    -0.59
     criteria
    -0.59
     agre
    -0.58
     pree
    -0.58
    POSITIVE LOGITS
    df
    0.84
    amin
    0.81
    oshi
    0.81
    hi
    0.80
    hz
    0.80
    oba
    0.80
    atz
    0.77
    mt
    0.77
    ESSION
    0.76
    hw
    0.75
    Activations Density 0.023%

    No Known Activations