© 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. 25978
    Prev
    Next
    INDEX
    Explanations

    words relating to economic hardship and struggles

    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
    362
    +0.14
    0.7%
    68
    +0.13
    0.6%
    481
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.05
    408
    +0.13
    0.05
    453
    +0.12
    0.04
    Negative Logits
    ittee
    -0.87
     tremend
    -0.84
    hander
    -0.83
    ouf
    -0.78
    keleton
    -0.78
    problem
    -0.78
    claimer
    -0.77
    ainer
    -0.77
    ITION
    -0.76
    ��
    -0.76
    POSITIVE LOGITS
     scenarios
    0.95
     proportions
    0.93
     backgrounds
    0.91
     environments
    0.90
     venues
    0.89
     chunks
    0.88
     groups
    0.87
     institutions
    0.87
     celebrities
    0.86
     situations
    0.86
    Activations Density 0.197%

    No Known Activations