© 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. 31200
    Prev
    Next
    INDEX
    Explanations

    words related to geopolitical tensions, government actions, and international relations

    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
    +0.14
    0.6%
    724
    +0.12
    0.5%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.14
    0.16
    61
    +0.12
    0.13
    282
    +0.11
    0.14
    Negative Logits
    .;
    -0.73
    nikov
    -0.70
    hatt
    -0.70
    cess
    -0.69
    .",
    -0.68
    chet
    -0.68
    aint
    -0.67
    gg
    -0.67
    lex
    -0.66
    cing
    -0.64
    POSITIVE LOGITS
     incidentally
    0.95
     presumably
    0.79
     bundled
    0.71
    Ö¼
    0.71
     admittedly
    0.70
     hereafter
    0.70
     overseen
    0.68
     ironically
    0.67
     hitherto
    0.66
     famously
    0.66
    Activations Density 12.233%

    No Known Activations