© 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. 2202
    Prev
    Next
    INDEX
    Explanations

    details about upcoming video game releases

    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
    480
    +0.36
    1.7%
    671
    +0.13
    0.6%
    120
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    671
    +0.36
    0.05
    480
    +0.13
    -0.01
    120
    +0.11
    0.05
    Negative Logits
     UNCLASSIFIED
    -0.71
    ullah
    -0.71
     constitutional
    -0.70
    zanne
    -0.69
     nonviolent
    -0.67
    bard
    -0.67
    ictionary
    -0.66
    ewater
    -0.66
     deport
    -0.66
    yll
    -0.66
    POSITIVE LOGITS
     teaser
    1.13
     Razer
    1.04
     Konami
    1.02
     Capcom
    1.02
     Ubisoft
    1.01
     devs
    1.00
     screenshots
    0.98
     previews
    0.97
     Nvidia
    0.97
     teased
    0.97
    Activations Density 1.242%

    No Known Activations