© 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 24576
    9. 8-RES_FS24576-JB
    11. 20232
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and government

    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
    620
    +0.10
    0.5%
    242
    +0.10
    0.5%
    350
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.10
    0.02
    350
    +0.10
    0.04
    506
    +0.10
    0.04
    Negative Logits
    livion
    -0.78
     inconsistency
    -0.74
    INAL
    -0.74
    dule
    -0.73
     overload
    -0.72
     PTS
    -0.72
    ipeg
    -0.70
    ciation
    -0.70
     Incident
    -0.70
    ãĤ¦ãĤ¹
    -0.70
    POSITIVE LOGITS
     billionaire
    1.45
     billionaires
    1.22
     lobbyist
    1.21
     finan
    1.17
     lobbying
    1.14
     lobbyists
    1.14
     businessmen
    1.12
     Goldman
    1.11
     philanthrop
    1.11
     Soros
    1.10
    Activations Density 0.706%

    No Known Activations