© 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. 18734
    Prev
    Next
    INDEX
    Explanations

    references to significant events or achievements

    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
    288
    +0.17
    0.8%
    554
    +0.10
    0.4%
    151
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.02
    554
    +0.10
    0.01
    151
    +0.09
    0.02
    Negative Logits
    gypt
    -0.87
    thia
    -0.80
    ieri
    -0.77
    ©¶æ
    -0.75
    yah
    -0.72
    nery
    -0.71
    udder
    -0.71
    gans
    -0.70
    thus
    -0.69
    cipl
    -0.69
    POSITIVE LOGITS
     landmark
    1.11
     achievement
    0.96
     preservation
    0.84
     accomplishment
    0.84
     achievements
    0.82
     breakthrough
    0.78
     milestone
    0.76
     accomplishments
    0.76
     announcement
    0.71
    stone
    0.71
    Activations Density 0.037%

    No Known Activations