© 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. 1500
    Prev
    Next
    INDEX
    Explanations

    names of politicians

    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
    530
    +0.10
    0.5%
    207
    +0.10
    0.4%
    645
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.10
    0.02
    645
    +0.10
    0.03
    153
    +0.09
    0.03
    Negative Logits
    tal
    -0.73
     ly
    -0.70
     lin
    -0.69
     brill
    -0.69
     enh
    -0.68
     babe
    -0.67
    roth
    -0.67
    har
    -0.67
     cylinder
    -0.67
     resil
    -0.67
    POSITIVE LOGITS
     Government
    0.96
     CIA
    0.93
     NATO
    0.90
     United
    0.90
     Conservative
    0.88
     Navy
    0.86
     GNU
    0.86
     US
    0.84
     NASA
    0.83
     Conservatives
    0.83
    Activations Density 0.163%

    No Known Activations