© 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 12288
    9. 8-RES_FS12288-JB
    11. 9507
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "amp."

    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
    526
    +0.11
    0.5%
    262
    +0.10
    0.5%
    113
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.03
    701
    +0.10
    0.02
    232
    +0.10
    0.02
    Negative Logits
    SHIP
    -0.85
    ignty
    -0.73
    ģĸ
    -0.72
    BLIC
    -0.70
     resemblance
    -0.68
    DOM
    -0.67
    çĭ
    -0.64
    ntax
    -0.64
    ryu
    -0.61
     circumst
    -0.60
    POSITIVE LOGITS
    aign
    1.27
    agne
    1.23
    hetamine
    1.11
    aic
    1.01
    arts
    1.00
    owered
    1.00
    oline
    0.95
    eters
    0.94
    acus
    0.93
    oons
    0.92
    Activations Density 0.082%

    No Known Activations