© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    commands or instructions

    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
    240
    +0.12
    0.5%
    611
    +0.11
    0.5%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.12
    0.03
    611
    +0.11
    0.03
    183
    +0.11
    0.03
    Negative Logits
     accompanies
    -0.79
     livest
    -0.69
     constitu
    -0.68
     advertised
    -0.66
     agre
    -0.64
    idding
    -0.61
    nesota
    -0.59
    nar
    -0.59
     coerc
    -0.58
     dissatisf
    -0.57
    POSITIVE LOGITS
    aways
    1.26
     advantage
    1.10
    away
    0.94
     heed
    0.93
    uchi
    0.91
     aback
    0.89
     care
    0.84
    overs
    0.82
    prising
    0.80
    frey
    0.75
    Activations Density 0.042%

    No Known Activations