© 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 1536
    9. 8-RES_FS1536-JB
    11. 1108
    Prev
    Next
    INDEX
    Explanations

    phrases related to patterns, order, and organization

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    7
    +0.10
    0.5%
    509
    +0.09
    0.4%
    235
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.10
    0.05
    288
    +0.09
    0.08
    222
    +0.09
    0.04
    Negative Logits
    tek
    -0.89
    lasses
    -0.84
    sonian
    -0.81
    tu
    -0.78
    attery
    -0.76
    vae
    -0.74
    kies
    -0.73
    ãĤ©
    -0.73
    ky
    -0.71
    iders
    -0.70
    POSITIVE LOGITS
    lies
    1.20
    etary
    0.97
    liness
    0.88
     fulfillment
    0.79
    eering
    0.75
    ordering
    0.70
     Mant
    0.68
     discipl
    0.64
     directs
    0.64
     Osw
    0.64
    Activations Density 2.119%

    No Known Activations