© 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 24576
    9. 8-RES_FS24576-JB
    11. 3683
    Prev
    Next
    INDEX
    Explanations

    legal terms and discussions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.20
    0.9%
    459
    +0.13
    0.6%
    705
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    705
    +0.20
    0.05
    228
    +0.13
    0.05
    69
    +0.10
    0.04
    Negative Logits
    aukee
    -0.89
    Laughs
    -0.84
    laughs
    -0.77
    alt
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    ggles
    -0.72
    achelor
    -0.71
    ãĤ´ãĥ³
    -0.71
    inki
    -0.70
    Bonus
    -0.69
    POSITIVE LOGITS
     inadequate
    0.88
     they
    0.88
     insufficient
    0.83
     excessive
    0.83
     improperly
    0.83
     improper
    0.80
     delaying
    0.80
     inaction
    0.79
     unfairly
    0.78
     unfair
    0.76
    Activations Density 0.212%

    No Known Activations