© 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. 22208
    Prev
    Next
    INDEX
    Explanations

    references to theater and gaming modes

    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
    +0.14
    0.7%
    683
    +0.10
    0.5%
    354
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.14
    0.01
    530
    +0.10
    0.01
    373
    +0.09
    -0.00
    Negative Logits
     retri
    -0.72
     mete
    -0.70
    arians
    -0.64
    ogy
    -0.64
     sacrific
    -0.63
    rals
    -0.60
     passer
    -0.60
     optic
    -0.59
    maid
    -0.59
     astron
    -0.58
    POSITIVE LOGITS
     Thumbnails
    1.05
     Mode
    0.88
     Theatre
    0.74
     Featured
    0.73
     IMAGES
    0.71
     Content
    0.71
     WATCHED
    0.66
     Below
    0.66
     Asylum
    0.65
     Transcript
    0.64
    Activations Density 0.013%

    No Known Activations