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

    Neuronpedia

    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 3072
    9. 8-RES_FS3072-JB
    11. 773
    Prev
    Next
    INDEX
    Explanations

    discussion related to politics and political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    288
    +0.15
    0.7%
    546
    +0.14
    0.6%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.15
    0.07
    288
    +0.14
    0.06
    667
    +0.10
    0.05
    Negative Logits
    actory
    -0.88
     Cancel
    -0.85
    imates
    -0.80
    wered
    -0.75
    olen
    -0.74
    tered
    -0.71
    wolves
    -0.70
    xt
    -0.70
    oa
    -0.68
     Ot
    -0.68
    POSITIVE LOGITS
     correctness
    1.42
     appoint
    0.92
     activism
    0.91
     pund
    0.90
     rhetoric
    0.88
     upheaval
    0.87
     intrig
    0.87
     clout
    0.86
     turmoil
    0.84
     affiliation
    0.84
    Activations Density 0.417%

    No Known Activations