© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    specific locations and events from news articles

    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
    87
    +0.29
    1.5%
    68
    +0.09
    0.5%
    569
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.11
    87
    +0.09
    -0.03
    251
    +0.08
    0.05
    Negative Logits
    ouf
    -0.63
    swer
    -0.60
     fielder
    -0.59
     microbiome
    -0.59
     logo
    -0.59
    ouple
    -0.58
    uristic
    -0.57
    uscript
    -0.57
     instance
    -0.57
    keleton
    -0.56
    POSITIVE LOGITS
     proportions
    0.98
     circles
    0.75
     folklore
    0.73
    speak
    0.72
     fame
    0.72
     heaven
    0.71
     supremacy
    0.69
    livion
    0.69
     emergencies
    0.67
     communism
    0.67
    Activations Density 0.914%

    No Known Activations