© 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. 24261
    Prev
    Next
    INDEX
    Explanations

    negations or negative constructs in a text

    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
    640
    +0.13
    0.6%
    314
    +0.12
    0.6%
    373
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.13
    0.02
    425
    +0.12
    0.02
    152
    +0.12
    0.02
    Negative Logits
     Sawyer
    -0.67
     Dia
    -0.66
     Illum
    -0.62
     Syl
    -0.61
     Cox
    -0.60
     Parenthood
    -0.60
     Pengu
    -0.59
     Strait
    -0.59
     vigil
    -0.58
     Manual
    -0.58
    POSITIVE LOGITS
    level
    1.26
    tier
    1.24
    ranking
    1.20
    ranked
    1.12
    class
    1.08
    selling
    1.08
    lining
    1.06
    performing
    1.05
    priority
    1.05
    heavy
    1.03
    Activations Density 0.019%

    No Known Activations