© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    instances where someone is focused on self-improvement or the improvement of a situation

    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
    507
    +0.10
    0.4%
    679
    +0.09
    0.4%
    575
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.10
    0.03
    751
    +0.09
    0.03
    766
    +0.09
    0.02
    Negative Logits
     Straw
    -0.77
    itto
    -0.72
    cia
    -0.69
    NetMessage
    -0.69
    runners
    -0.68
    ansas
    -0.66
    cium
    -0.64
    dor
    -0.64
    beck
    -0.64
    til
    -0.64
    POSITIVE LOGITS
     efficiency
    1.01
     responsiveness
    0.94
     productivity
    0.92
    ments
    0.91
     acquainted
    0.84
    iating
    0.81
     quality
    0.81
     markedly
    0.80
     materially
    0.79
     relations
    0.76
    Activations Density 0.090%

    No Known Activations