© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24509
    Prev
    Next
    INDEX
    Explanations

    references to the name "Chen."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    276
    +0.10
    0.5%
    332
    +0.10
    0.4%
    587
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.02
    99
    +0.10
    0.01
    343
    +0.09
    0.01
    Negative Logits
    JECT
    -0.71
    ãĥĨ
    -0.69
    ����
    -0.64
    rocal
    -0.60
     saline
    -0.59
    teen
    -0.59
    LEASE
    -0.58
    gamer
    -0.58
    Results
    -0.58
    Body
    -0.57
    POSITIVE LOGITS
     Guang
    1.03
     Chang
    0.95
    igans
    0.89
    ault
    0.89
    nai
    0.86
     Xiang
    0.82
     Chen
    0.81
    zhou
    0.80
    iere
    0.79
    obyl
    0.78
    Activations Density 0.033%

    No Known Activations