© 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. 7623
    Prev
    Next
    INDEX
    Explanations

    politically related terms or mentions, specifically regarding impeachment 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_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
    288
    +0.18
    0.8%
    701
    +0.13
    0.6%
    311
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.18
    0.02
    311
    +0.13
    0.01
    288
    +0.11
    0.01
    Negative Logits
    BLE
    -0.74
    enegger
    -0.73
    ecause
    -0.70
    EEE
    -0.66
     Dragonbound
    -0.66
    nces
    -0.65
    ãģ¦
    -0.65
    manship
    -0.64
    ãĤĭ
    -0.63
    loo
    -0.63
    POSITIVE LOGITS
    itude
    1.38
    ogether
    1.36
    itudes
    1.34
    itud
    1.33
    itudinal
    1.17
    imore
    1.10
    uve
    0.97
    imeter
    0.97
    imately
    0.84
    imeters
    0.83
    Activations Density 0.016%

    No Known Activations