© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8741
    Prev
    Next
    INDEX
    Explanations

    information related to government policies and political issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.15
    0.5%
    482
    +0.14
    0.5%
    544
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.15
    -0.09
    739
    +0.14
    0.03
    267
    +0.14
    0.06
    Negative Logits
    thus
    -0.81
    Oracle
    -0.80
    Recipe
    -0.79
     reprint
    -0.78
    YouTube
    -0.75
     toler
    -0.73
    Cooldown
    -0.73
    Cola
    -0.73
    surv
    -0.72
    ione
    -0.72
    POSITIVE LOGITS
    ursday
    0.86
    cellaneous
    0.86
    CLASSIFIED
    0.83
     TBD
    0.81
     Lastly
    0.80
     ado
    0.79
    BLIC
    0.78
    ymm
    0.77
     distractions
    0.77
    =-=-=-=-
    0.77
    Activations Density 2.241%

    No Known Activations