© 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. 19480
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements in a recipe

    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
    314
    +0.12
    0.5%
    187
    +0.10
    0.5%
    242
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    23
    +0.10
    0.03
    95
    +0.10
    0.02
    Negative Logits
     nonexistent
    -0.61
     superst
    -0.60
     disinfect
    -0.60
     compare
    -0.60
     comparisons
    -0.60
     prost
    -0.58
     murd
    -0.58
     Allaah
    -0.57
     RTX
    -0.55
     Allah
    -0.54
    POSITIVE LOGITS
    hz
    1.02
    bps
    0.91
    ategory
    0.82
    +)
    0.82
    +,
    0.80
    rs
    0.80
    +.
    0.78
    GS
    0.77
    bs
    0.76
    +
    0.76
    Activations Density 0.060%

    No Known Activations