© 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. 36988
    Prev
    Next
    INDEX
    Explanations

    terms related to war, conflict, and political tensions

    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
    +0.12
    0.6%
    546
    +0.10
    0.5%
    226
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.29
    546
    +0.10
    0.11
    6
    +0.10
    0.15
    Negative Logits
    */(
    -0.67
    ilts
    -0.63
    rac
    -0.63
    )=(
    -0.62
     balcon
    -0.62
     Helpful
    -0.61
    veland
    -0.60
    ograp
    -0.60
    ciating
    -0.59
    igans
    -0.59
    POSITIVE LOGITS
    enegger
    0.85
    schild
    0.80
     Armageddon
    0.72
     Afghanistan
    0.71
     waged
    0.71
     raged
    0.68
     attrition
    0.67
     Yugoslavia
    0.67
    adesh
    0.66
     Vietnam
    0.64
    Activations Density 16.766%

    No Known Activations