© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31312
    Prev
    Next
    INDEX
    Explanations

    text related to political campaigns, campaign finance, donations, and political influence

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.13
    0.6%
    666
    +0.11
    0.5%
    442
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.10
    620
    +0.11
    0.01
    310
    +0.10
    0.08
    Negative Logits
    terness
    -0.76
     Osaka
    -0.73
    ĨĴ
    -0.71
     Clockwork
    -0.71
     Yi
    -0.70
    ĸļ
    -0.69
     deterior
    -0.68
     Fukushima
    -0.68
     systemd
    -0.68
    seless
    -0.65
    POSITIVE LOGITS
     PACs
    1.08
     donors
    1.05
     fundraising
    1.03
     fundra
    1.02
     donations
    0.98
     lobbying
    0.97
     endorsements
    0.96
    aires
    0.95
     donor
    0.94
     funnel
    0.94
    Activations Density 9.796%

    No Known Activations