© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23989
    Prev
    Next
    INDEX
    Explanations

    questions about processes, reasons, and usage instructions

    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
    496
    +0.12
    0.6%
    144
    +0.10
    0.5%
    92
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.12
    0.04
    60
    +0.10
    0.04
    186
    +0.09
    0.04
    Negative Logits
    ĸļ
    -0.69
    20439
    -0.66
    ously
    -0.65
    uther
    -0.63
    gi
    -0.63
    tn
    -0.63
    efully
    -0.62
     somehow
    -0.62
     frankly
    -0.61
    ¯
    -0.61
    POSITIVE LOGITS
     Difference
    0.96
     Benefits
    0.94
     Definitions
    0.91
     Uses
    0.91
     Overview
    0.89
     Makes
    0.88
     Functions
    0.88
     Own
    0.87
     Particip
    0.87
     Documents
    0.86
    Activations Density 0.146%

    No Known Activations