© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    the word "juror"

    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
    588
    +0.09
    0.4%
    4
    +0.07
    0.4%
    600
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    626
    +0.09
    0.02
    373
    +0.07
    -0.01
    514
    +0.07
    0.02
    Negative Logits
     Beautiful
    -0.70
    yip
    -0.67
     Ingram
    -0.59
     Wonders
    -0.59
    Bey
    -0.59
     Zimmer
    -0.58
     Wicked
    -0.58
     Wick
    -0.57
     toast
    -0.57
    hedral
    -0.57
    POSITIVE LOGITS
    anic
    0.67
    ilit
    0.64
    reprene
    0.62
     prosecut
    0.62
    iatrics
    0.62
    Īè
    0.60
    iscons
    0.58
    ²¾
    0.57
    isc
    0.56
     administr
    0.55
    Activations Density 0.111%

    No Known Activations