© 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. 13365
    Prev
    Next
    INDEX
    Explanations

    phrases related to political controversies and conflicts

    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
    314
    +0.11
    0.5%
    20
    +0.10
    0.5%
    514
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.11
    0.10
    327
    +0.10
    0.09
    514
    +0.10
    0.09
    Negative Logits
     decomp
    -0.81
     JPEG
    -0.76
     silhou
    -0.70
     +++
    -0.61
     gib
    -0.61
     photoc
    -0.59
     scrut
    -0.55
     Axel
    -0.55
     scrim
    -0.54
     whistle
    -0.54
    POSITIVE LOGITS
    s
    1.31
    tal
    1.03
    ski
    1.02
    selves
    0.97
    ses
    0.96
    tarian
    0.94
    tsy
    0.91
    ese
    0.90
    ship
    0.90
    ties
    0.90
    Activations Density 0.233%

    No Known Activations