© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 4192
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms related to citizenship, amnesty, and political party affiliation

    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
    640
    +0.20
    0.9%
    373
    +0.15
    0.7%
    247
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.07
    143
    +0.15
    0.05
    6
    +0.09
    0.05
    Negative Logits
    recy
    -0.71
    social
    -0.65
    arde
    -0.62
    ighth
    -0.62
    rac
    -0.61
    uesday
    -0.60
     hiber
    -0.60
     Skydragon
    -0.59
     fres
    -0.59
     estranged
    -0.58
    POSITIVE LOGITS
    ³³³
    0.69
     Said
    0.68
    ONSORED
    0.67
    Answer
    0.65
    ³³³³
    0.65
    ³³³³³³³³
    0.64
    Solution
    0.62
     Tee
    0.62
     âĢķ
    0.61
    ↵
    0.57
    Activations Density 0.144%

    No Known Activations