© 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. 2976
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or negative judgment

    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
    746
    +0.14
    0.6%
    67
    +0.13
    0.6%
    251
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.14
    0.02
    251
    +0.13
    0.02
    503
    +0.13
    0.01
    Negative Logits
    tery
    -0.83
    ĪĴ
    -0.70
    MENT
    -0.69
    uyomi
    -0.68
    Ò
    -0.67
    MENTS
    -0.67
    pad
    -0.66
    姫
    -0.65
    ãĥĦ
    -0.64
    ku
    -0.64
    POSITIVE LOGITS
    onduct
    1.35
    ursed
    1.33
    redited
    1.30
    ategor
    1.24
    aleb
    1.23
    overed
    1.19
    ounter
    1.18
    oded
    1.18
    ooked
    1.16
    ount
    1.16
    Activations Density 0.019%

    No Known Activations