© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    information related to urban development and infrastructure projects

    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
    373
    +0.17
    0.8%
    530
    +0.10
    0.5%
    520
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.17
    0.02
    520
    +0.10
    0.02
    40
    +0.10
    0.02
    Negative Logits
    cest
    -0.71
    venge
    -0.63
    è¦ļéĨĴ
    -0.62
    itive
    -0.60
    crit
    -0.58
    Writ
    -0.57
    ointed
    -0.57
    OH
    -0.56
    XL
    -0.56
    kn
    -0.56
    POSITIVE LOGITS
     advertisement
    0.90
     slideshow
    0.78
     Thumbnails
    0.72
    imeo
    0.71
     Pinterest
    0.69
     âĨ
    0.69
     Loading
    0.68
     slide
    0.66
     gallery
    0.64
     sidebar
    0.63
    Activations Density 0.012%

    No Known Activations