© 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. 212
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or confusion

    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
    592
    +0.10
    0.5%
    172
    +0.10
    0.4%
    556
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.10
    0.06
    566
    +0.10
    0.05
    49
    +0.10
    0.05
    Negative Logits
    tyard
    -0.72
    atl
    -0.71
    rawdownloadcloneembedreportprint
    -0.67
     Moroc
    -0.61
    zes
    -0.60
    tions
    -0.59
    vik
    -0.59
    htaking
    -0.59
     Hass
    -0.58
    ersive
    -0.58
    POSITIVE LOGITS
    morrow
    0.83
    azo
    0.76
     damn
    0.73
     surely
    0.70
     okay
    0.68
     darn
    0.66
     automatically
    0.66
     likely
    0.65
    reed
    0.63
     ok
    0.62
    Activations Density 0.401%

    No Known Activations