© 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. 24173
    Prev
    Next
    INDEX
    Explanations

    variable declarations and function definitions in programming code

    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
    +0.12
    0.6%
    733
    +0.11
    0.5%
    176
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.12
    0.01
    31
    +0.11
    0.02
    692
    +0.10
    0.01
    Negative Logits
    advertising
    -0.77
    ocene
    -0.77
    flies
    -0.72
    papers
    -0.71
    د
    -0.70
    ingen
    -0.70
    skirts
    -0.70
    assic
    -0.70
    à¦
    -0.69
    gard
    -0.69
    POSITIVE LOGITS
     tmp
    0.85
     inline
    0.84
     seq
    0.81
     params
    0.81
     fn
    0.79
     ptr
    0.75
     __
    0.74
     obj
    0.74
     cp
    0.74
     vec
    0.73
    Activations Density 0.025%

    No Known Activations