© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9591
    Prev
    Next
    INDEX
    Explanations

    information related to political campaigns and election results

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    71
    +0.13
    0.6%
    197
    +0.11
    0.5%
    350
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.13
    0.04
    310
    +0.11
    0.05
    488
    +0.10
    0.05
    Negative Logits
     rehab
    -0.79
    artifacts
    -0.79
    odcast
    -0.69
    obyl
    -0.68
     offseason
    -0.66
    atech
    -0.64
     histories
    -0.63
     treat
    -0.63
     burner
    -0.63
     supplement
    -0.63
    POSITIVE LOGITS
     votes
    1.37
    votes
    1.25
     Votes
    1.17
     margin
    1.15
     vote
    1.14
    vote
    1.03
     voting
    1.02
     Electoral
    1.01
     Voting
    0.96
     polled
    0.96
    Activations Density 0.378%

    No Known Activations