© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4524
    Prev
    Next
    INDEX
    Explanations

    news articles about legal, political, and security topics

    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
    594
    +0.11
    0.5%
    387
    +0.10
    0.5%
    135
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.11
    0.05
    121
    +0.10
    0.05
    135
    +0.10
    0.05
    Negative Logits
    ©¶æ¥µ
    -0.77
    76561
    -0.74
    etheless
    -0.68
    ãĥĥãĥī
    -0.66
    Ħ¢
    -0.63
    Ī
    -0.63
    Need
    -0.62
    olar
    -0.62
    Ͻ
    -0.61
    Ĥİ
    -0.61
    POSITIVE LOGITS
    window
    0.95
     gestures
    0.89
     poses
    0.82
     pose
    0.80
     Photographer
    0.78
     logos
    0.78
     reacts
    0.77
     REUTERS
    0.75
     logo
    0.75
     IMAGES
    0.75
    Activations Density 0.362%

    No Known Activations