© 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. 15343
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation or judgment

    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
    724
    +0.10
    0.5%
    447
    +0.10
    0.4%
    252
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.10
    0.07
    575
    +0.10
    0.05
    540
    +0.10
    0.05
    Negative Logits
    ZI
    -0.61
    ighth
    -0.61
    rug
    -0.59
    IDA
    -0.59
    gart
    -0.58
    gars
    -0.58
    ogi
    -0.57
    auga
    -0.56
    cade
    -0.56
    ĪĴ
    -0.56
    POSITIVE LOGITS
    notations
    0.79
     whatsoever
    0.75
    tones
    0.74
     unlike
    0.68
     ranging
    0.67
     compared
    0.67
     depending
    0.66
     meanings
    0.66
     Attribution
    0.65
     comparable
    0.63
    Activations Density 0.261%

    No Known Activations