© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 25973
    Prev
    Next
    INDEX
    Explanations

    criticism of political figures and institutions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    Neuron Alignment
    Index
    Value
    % of L₁
    682
    +0.11
    0.5%
    620
    +0.10
    0.5%
    113
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.11
    0.01
    394
    +0.10
    0.01
    31
    +0.10
    0.01
    Negative Logits
    gow
    -0.81
    zac
    -0.76
    essee
    -0.69
    yip
    -0.69
    ovember
    -0.67
    ividual
    -0.65
    seys
    -0.65
    iewicz
    -0.63
    jri
    -0.62
    matter
    -0.62
    POSITIVE LOGITS
     collapsing
    0.64
    thumbnails
    0.62
    NVIDIA
    0.58
    Asset
    0.57
    Running
    0.57
     Rossi
    0.56
    Heart
    0.56
     Kend
    0.55
    ooters
    0.55
     intertwined
    0.55
    Activations Density 0.006%

    No Known Activations