© 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. 22416
    Prev
    Next
    INDEX
    Explanations

    question formats and inquiry phrases

    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
    373
    +0.16
    0.7%
    649
    +0.11
    0.5%
    426
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.16
    0.02
    373
    +0.11
    -0.01
    159
    +0.11
    0.02
    Negative Logits
    hung
    -0.68
     housed
    -0.59
     padd
    -0.59
     stranded
    -0.59
     screws
    -0.59
    wcs
    -0.59
     partying
    -0.58
    guards
    -0.57
    angering
    -0.56
     reins
    -0.56
    POSITIVE LOGITS
     GOODMAN
    1.10
     Continued
    0.91
     Conclusion
    0.88
    Question
    0.86
    ertodd
    0.84
     References
    0.80
     Expand
    0.79
     Question
    0.78
     Solution
    0.78
    Myth
    0.77
    Activations Density 0.096%

    No Known Activations