© 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. 22504
    Prev
    Next
    INDEX
    Explanations

    verbs related to reactions or responses to various situations

    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
    140
    +0.10
    0.4%
    405
    +0.10
    0.4%
    41
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.05
    641
    +0.10
    0.04
    405
    +0.09
    0.03
    Negative Logits
    auga
    -0.79
    uphem
    -0.70
    cpp
    -0.65
    gart
    -0.65
    £ı
    -0.65
    iciency
    -0.64
    auc
    -0.63
    livion
    -0.61
    arters
    -0.59
    sav
    -0.59
    POSITIVE LOGITS
     differs
    0.70
     interacting
    0.70
     RTX
    0.67
     Different
    0.67
     reacting
    0.66
     interacts
    0.65
     interact
    0.65
     relation
    0.65
     regard
    0.64
     Millenn
    0.64
    Activations Density 0.186%

    No Known Activations