© 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 24576
    9. 8-RES_FS24576-JB
    11. 11861
    Prev
    Next
    INDEX
    Explanations

    words related to technology and programming

    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
    314
    +0.13
    0.6%
    129
    +0.12
    0.5%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.05
    129
    +0.12
    0.05
    289
    +0.11
    0.02
    Negative Logits
     exception
    -0.68
     Submission
    -0.61
     visitation
    -0.61
     submission
    -0.61
    's
    -0.60
     CPR
    -0.59
     arrivals
    -0.59
     jurisdiction
    -0.59
     Portuguese
    -0.58
     adjunct
    -0.58
    POSITIVE LOGITS
    pace
    1.72
    creen
    1.66
    peed
    1.62
    hift
    1.62
    chool
    1.60
    mith
    1.59
    ilver
    1.57
    pring
    1.55
    cale
    1.53
    heet
    1.48
    Activations Density 0.298%

    No Known Activations