© 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. 10704
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocating for a cause or belief, particularly about government and society

    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
    496
    +0.11
    0.5%
    477
    +0.10
    0.4%
    122
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.11
    0.04
    122
    +0.10
    0.05
    498
    +0.09
    0.04
    Negative Logits
    ppings
    -0.90
    later
    -0.81
    umably
    -0.77
     worse
    -0.74
    oshenko
    -0.70
    metadata
    -0.68
     yawn
    -0.68
    older
    -0.67
    etter
    -0.67
    Putin
    -0.67
    POSITIVE LOGITS
     strives
    1.14
     excellence
    1.06
     collabor
    1.01
     Excellence
    0.98
     strive
    0.98
     proudly
    0.97
     dedicated
    0.97
     accredited
    0.92
     specializing
    0.91
     Certified
    0.91
    Activations Density 0.643%

    No Known Activations