© 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. 26690
    Prev
    Next
    INDEX
    Explanations

    references to government health and human services

    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
    +0.14
    0.7%
    299
    +0.09
    0.5%
    726
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.03
    373
    +0.09
    -0.01
    299
    +0.09
    0.02
    Negative Logits
    Äĩ
    -0.68
    è£ħ
    -0.67
     guiActive
    -0.61
    ĪĴ
    -0.60
     scrut
    -0.58
     Vengeance
    -0.57
    EStreamFrame
    -0.56
     swast
    -0.54
     unch
    -0.54
    ĨĴ
    -0.53
    POSITIVE LOGITS
    isons
    0.57
     Cyrus
    0.57
    atoes
    0.56
    oppers
    0.55
    monds
    0.54
    isible
    0.54
    azines
    0.53
    adden
    0.51
    aney
    0.50
     endangered
    0.50
    Activations Density 0.093%

    No Known Activations