© 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. 22462
    Prev
    Next
    INDEX
    Explanations

    adverbs that indicate degrees of certainty or intensity

    oai_token-act-pair · gpt-4o-miniTriggered 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
    724
    +0.11
    0.5%
    192
    +0.11
    0.5%
    607
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.06
    760
    +0.11
    0.04
    214
    +0.09
    0.04
    Negative Logits
     Library
    -0.66
    ription
    -0.63
     caption
    -0.61
     psyche
    -0.60
     Exhibition
    -0.60
    olis
    -0.59
     proclamation
    -0.59
     Religion
    -0.58
     Plugin
    -0.58
     Ruler
    -0.58
    POSITIVE LOGITS
    limited
    0.85
    undreds
    0.84
     disparate
    0.84
    traditional
    0.79
    adequ
    0.78
    different
    0.78
    significant
    0.77
     fewer
    0.77
    reasonable
    0.76
    zero
    0.74
    Activations Density 0.257%

    No Known Activations