© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1377
    Prev
    Next
    INDEX
    Explanations

    details related to technical issues, lawsuits, and social media interactions

    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
    87
    +0.33
    1.7%
    756
    +0.15
    0.8%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.33
    -0.02
    756
    +0.15
    -0.03
    679
    +0.10
    0.08
    Negative Logits
     electr
    -0.74
    omics
    -0.70
     famine
    -0.69
     blending
    -0.66
     buildup
    -0.65
     nuclear
    -0.65
     ascend
    -0.65
     immortality
    -0.63
     summers
    -0.62
     astronaut
    -0.62
    POSITIVE LOGITS
     DMCA
    1.02
     refund
    1.01
     Pastebin
    0.99
     emailed
    0.96
     contacted
    0.93
     refunds
    0.90
     complainant
    0.89
     admins
    0.88
     contacting
    0.86
     redacted
    0.86
    Activations Density 1.025%

    No Known Activations