© 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. 7694
    Prev
    Next
    INDEX
    Explanations

    references to the musician "Bonnie" or mentions of his related activities

    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
    526
    +0.15
    0.7%
    343
    +0.14
    0.6%
    421
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.15
    0.02
    421
    +0.14
    0.02
    232
    +0.13
    0.02
    Negative Logits
    dfx
    -0.85
    UGE
    -0.72
    INAL
    -0.67
    ELD
    -0.66
    TY
    -0.64
    ãĥĥãĥī
    -0.64
    REAM
    -0.63
    gamer
    -0.61
     Ethics
    -0.60
    æĸ¹
    -0.59
    POSITIVE LOGITS
    anza
    1.17
    uses
    1.12
    iton
    1.10
    itors
    1.06
    eless
    1.02
    anz
    1.00
    obo
    0.96
    obos
    0.96
    gey
    0.95
    neau
    0.94
    Activations Density 0.016%

    No Known Activations