© 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. 10582
    Prev
    Next
    INDEX
    Explanations

    information about technology and science advancements

    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
    640
    +0.13
    0.6%
    59
    +0.12
    0.6%
    314
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.13
    0.03
    59
    +0.12
    0.03
    211
    +0.12
    0.02
    Negative Logits
    assetsadobe
    -0.67
     Wem
    -0.64
     Rover
    -0.60
     Bulg
    -0.58
    OHN
    -0.58
    gypt
    -0.58
     wip
    -0.57
     Ones
    -0.57
     calves
    -0.57
     practicable
    -0.57
    POSITIVE LOGITS
    venient
    1.34
    ventional
    1.32
    structed
    1.29
    ventions
    1.29
    crete
    1.28
    stant
    1.28
    secut
    1.27
    clusions
    1.25
    cerned
    1.21
    cern
    1.20
    Activations Density 0.057%

    No Known Activations