© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18711
    Prev
    Next
    INDEX
    Explanations

    instances where there are reports or cases of particular events happening

    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
    447
    +0.19
    0.9%
    71
    +0.12
    0.5%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.19
    0.04
    126
    +0.12
    0.04
    395
    +0.10
    0.03
    Negative Logits
    UME
    -0.85
    urden
    -0.77
    anium
    -0.69
    onto
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
     2020
    -0.67
    ater
    -0.66
    \-
    -0.66
    ens
    -0.64
    isma
    -0.62
    POSITIVE LOGITS
     instances
    0.97
     examples
    0.93
     unintended
    0.91
     anecdotal
    0.87
     unintentional
    0.86
     attempts
    0.86
     conflicting
    0.84
     glimps
    0.84
     complaints
    0.84
     inadvert
    0.83
    Activations Density 0.326%

    No Known Activations