© 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. 9151
    Prev
    Next
    INDEX
    Explanations

    information related to historical figures or individuals and their relationships

    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
    375
    +0.11
    0.5%
    512
    +0.10
    0.4%
    80
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    543
    +0.11
    0.03
    362
    +0.10
    0.04
    528
    +0.09
    0.03
    Negative Logits
     deterrent
    -0.83
    wcs
    -0.82
     audits
    -0.79
     citations
    -0.75
     redund
    -0.74
     obser
    -0.74
     prosecutions
    -0.74
     deterrence
    -0.74
     calibration
    -0.73
     skies
    -0.72
    POSITIVE LOGITS
     Samantha
    0.96
     Molly
    0.88
     Jessica
    0.88
     Ginny
    0.86
     girlfriend
    0.86
     Sophie
    0.86
     Barbie
    0.85
     prostitutes
    0.85
     Valerie
    0.85
     Eva
    0.84
    Activations Density 0.181%

    No Known Activations