© 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 EvalsExportsinterp-engineNEWAPI 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. 16320
    Prev
    Next
    INDEX
    Explanations

    words related to opinions and judgments, particularly ones expressing strong feelings like intrigue, importance, and relevance

    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
    679
    +0.11
    0.5%
    14
    +0.10
    0.4%
    28
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.11
    0.04
    566
    +0.10
    0.06
    274
    +0.10
    0.05
    Negative Logits
    por
    -0.80
    arta
    -0.79
    cedented
    -0.78
    veland
    -0.78
    opus
    -0.76
    enta
    -0.73
    enegger
    -0.73
    yet
    -0.71
    yah
    -0.71
    eston
    -0.68
    POSITIVE LOGITS
    DEV
    0.78
     initially
    0.75
     originally
    0.71
     beforehand
    0.66
     earlier
    0.66
     tremend
    0.64
     unsuccessfully
    0.63
     Soviet
    0.61
     previously
    0.60
    wolves
    0.60
    Activations Density 0.570%

    No Known Activations