© 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 EvalsExportsAPI 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. 8910
    Prev
    Next
    INDEX
    Explanations

    references to specific newspapers such as "The Washington Post" and "The New York Times"

    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
    481
    +0.24
    1.1%
    419
    +0.12
    0.6%
    171
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.24
    0.05
    346
    +0.12
    0.05
    419
    +0.10
    0.05
    Negative Logits
    conservancy
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
     veto
    -0.70
    locks
    -0.67
     ç¥ŀ
    -0.65
     Leilan
    -0.65
    âĻ¥
    -0.65
     masc
    -0.65
    wcs
    -0.64
    unia
    -0.64
    POSITIVE LOGITS
     report
    1.12
     analysis
    1.01
     findings
    0.97
     estimates
    0.95
     analyzed
    0.95
     reports
    0.94
     estimate
    0.93
     analyses
    0.93
     conclusion
    0.93
     speculate
    0.92
    Activations Density 0.538%

    No Known Activations