© 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 12288
    5. 8-RES_FS12288-JB
    6. 10843
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific company and related developments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    205
    +0.12
    0.5%
    513
    +0.11
    0.5%
    651
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.09
    205
    +0.11
    0.05
    575
    +0.11
    0.07
    Negative Logits
    adish
    -0.69
    actionDate
    -0.67
     ISBN
    -0.67
    wered
    -0.65
     corpses
    -0.65
     candles
    -0.64
     Cosponsors
    -0.61
    aughs
    -0.61
    nces
    -0.59
     prostitutes
    -0.59
    POSITIVE LOGITS
     endeavour
    0.94
     endeavor
    0.87
    igsaw
    0.85
     repertoire
    0.83
    yssey
    0.81
     puzzle
    0.81
     constellation
    0.79
     saga
    0.78
     ecosystem
    0.78
     mythology
    0.76
    Activations Density 0.840%

    No Known Activations