© 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. 13759
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with 'of' that are related to various topics such as social issues, government practices, and health concerns

    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
    403
    +0.11
    0.5%
    413
    +0.10
    0.4%
    362
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.11
    0.02
    362
    +0.10
    0.02
    403
    +0.09
    0.02
    Negative Logits
    roots
    -0.93
     Aires
    -0.89
    æĦ
    -0.86
    selves
    -0.85
    minus
    -0.83
    redients
    -0.82
    uries
    -0.80
    ãĥķãĤ©
    -0.75
    cules
    -0.74
    äºĶ
    -0.72
    POSITIVE LOGITS
     occurrence
    1.15
     attrition
    1.00
     decline
    0.99
     deterioration
    0.92
     incidence
    0.92
     incarceration
    0.89
     attainment
    0.83
     progress
    0.83
     uptake
    0.82
     erosion
    0.82
    Activations Density 0.068%

    No Known Activations