© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 24233
    Prev
    Next
    INDEX
    Explanations

    words that contain the substring "ine"

    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
    +0.10
    0.5%
    407
    +0.10
    0.4%
    141
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.01
    232
    +0.10
    0.04
    284
    +0.09
    0.04
    Negative Logits
    assetsadobe
    -0.71
    luaj
    -0.68
     lash
    -0.65
     belts
    -0.62
     liaison
    -0.60
     Remastered
    -0.59
     unaff
    -0.58
     ambush
    -0.58
     bonded
    -0.57
     crib
    -0.57
    POSITIVE LOGITS
    hent
    0.91
    heit
    0.85
    velt
    0.84
    berg
    0.83
    bourg
    0.82
    arten
    0.82
    enberg
    0.79
    mann
    0.79
    lich
    0.78
    enthal
    0.76
    Activations Density 0.097%

    No Known Activations