© 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. 5858
    Prev
    Next
    INDEX
    Explanations

    texts related to political comments

    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
    756
    +0.15
    0.7%
    570
    +0.11
    0.5%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.15
    0.04
    86
    +0.11
    0.05
    756
    +0.09
    -0.03
    Negative Logits
    ãĤ¨ãĥ«
    -0.66
    addon
    -0.64
    odied
    -0.62
     famously
    -0.62
     guitarist
    -0.61
     stylish
    -0.60
     Alpine
    -0.60
    interstitial
    -0.60
     famed
    -0.59
     Romantic
    -0.59
    POSITIVE LOGITS
     ..."
    1.25
    )."
    1.01
     ['
    0.98
     âĢ¦"
    0.98
    ..."
    0.96
     [
    0.94
    .""
    0.93
    [/
    0.91
    .''
    0.90
     [/
    0.87
    Activations Density 1.246%

    No Known Activations