© 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. 11874
    Prev
    Next
    INDEX
    Explanations

    phrases related to commissioned tasks or projects

    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
    496
    +0.13
    0.6%
    339
    +0.11
    0.5%
    69
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.13
    0.01
    69
    +0.11
    0.01
    149
    +0.10
    0.01
    Negative Logits
    amac
    -0.74
    oland
    -0.71
    oya
    -0.70
    ophon
    -0.70
    corn
    -0.68
    bul
    -0.68
    tub
    -0.68
    acca
    -0.66
    eki
    -0.65
    fast
    -0.64
    POSITIVE LOGITS
     commissioned
    0.87
     commissions
    0.82
     artwork
    0.79
    smanship
    0.77
    isition
    0.76
    inates
    0.70
     commission
    0.69
     auction
    0.69
     permission
    0.66
    eer
    0.66
    Activations Density 0.034%

    No Known Activations