© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 13115
    Prev
    Next
    INDEX
    Explanations

    terms related to cultural heritage, property, hair and eye colors, security and safety, work, services, economy, precision, privacy, and motivation

    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
    762
    +0.14
    0.6%
    4
    +0.10
    0.5%
    79
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.14
    0.06
    225
    +0.10
    0.06
    575
    +0.10
    0.06
    Negative Logits
    izon
    -0.72
    pload
    -0.62
     Plaza
    -0.60
    ivo
    -0.57
    otin
    -0.56
    otropic
    -0.56
    erning
    -0.56
    CCC
    -0.54
     *)
    -0.54
    witz
    -0.54
    POSITIVE LOGITS
     alike
    1.12
     respectively
    1.05
     selves
    1.04
     counterparts
    0.82
     holdings
    0.77
     abilities
    0.75
     habits
    0.73
     combo
    0.71
     accordingly
    0.71
     preferences
    0.71
    Activations Density 0.263%

    No Known Activations