© 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 49152
    9. 8-RES_FS49152-JB
    11. 45672
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms related to news and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.19
    0.9%
    474
    +0.11
    0.5%
    675
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.19
    -0.00
    530
    +0.11
    0.01
    521
    +0.08
    0.01
    Negative Logits
    backer
    -0.73
    println
    -0.58
     Kappa
    -0.56
     Compton
    -0.55
    chair
    -0.53
     Honest
    -0.53
    artifacts
    -0.53
     Treasure
    -0.52
     prol
    -0.51
     slot
    -0.51
    POSITIVE LOGITS
    ENE
    0.78
    ongyang
    0.78
    ILLE
    0.77
    afety
    0.73
    acan
    0.72
    ENA
    0.72
    doms
    0.70
    Ãį
    0.69
     Lumpur
    0.68
    enes
    0.67
    Activations Density 0.008%

    No Known Activations