© 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 12288
    9. 8-RES_FS12288-JB
    11. 9394
    Prev
    Next
    INDEX
    Explanations

    sentences expressing strong emotional opinions or reactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    634
    +0.12
    0.5%
    402
    +0.11
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.12
    0.04
    55
    +0.11
    0.04
    634
    +0.10
    0.04
    Negative Logits
    NOTE
    -0.68
    ãģ®ç
    -0.65
    Products
    -0.64
    Footnote
    -0.61
    Ô
    -0.59
     Decay
    -0.58
    âĿ
    -0.57
    è¦ļéĨĴ
    -0.57
     è£ıç
    -0.57
     disputes
    -0.56
    POSITIVE LOGITS
    webkit
    0.75
     hypot
    0.74
    wolves
    0.65
    eret
    0.64
     somehow
    0.64
    lasses
    0.64
     tomorrow
    0.63
    nt
    0.63
     someday
    0.61
    essors
    0.60
    Activations Density 0.180%

    No Known Activations