© 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. 9056
    Prev
    Next
    INDEX
    Explanations

    mentions of debate moderators

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    746
    +0.04
    0.6%
    104
    +0.04
    0.5%
    343
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.04
    0.09
    104
    +0.04
    0.04
    224
    +0.03
    0.05
    Negative Logits
    åĮ
    -0.29
    OTAL
    -0.28
    INESS
    -0.24
    çīĪ
    -0.22
    EMA
    -0.22
    EMS
    -0.22
     Franch
    -0.21
    Sensor
    -0.21
    REE
    -0.21
     Winds
    -0.21
    POSITIVE LOGITS
     moder
    0.31
     moderators
    0.29
     moderator
    0.24
    ellen
    0.24
     Elaine
    0.22
    dl
    0.21
    aman
    0.21
    ipolar
    0.21
     reinstated
    0.20
    iquette
    0.20
    Activations Density 0.780%

    No Known Activations