© 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. 10404
    Prev
    Next
    INDEX
    Explanations

    specific numerical patterns that represent some kind of categorization or index

    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
    447
    +0.21
    0.8%
    572
    +0.16
    0.6%
    725
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.21
    0.01
    719
    +0.16
    0.01
    326
    +0.15
    0.01
    Negative Logits
     Ju
    -0.83
     Sho
    -0.79
    inous
    -0.78
     Polo
    -0.77
     Cosmetic
    -0.74
     Shap
    -0.74
    fit
    -0.73
     Saud
    -0.73
     Ple
    -0.71
     Suarez
    -0.71
    POSITIVE LOGITS
    imore
    0.86
    ttle
    0.82
    emphasis
    0.80
     ridden
    0.80
    arge
    0.80
    uckles
    0.78
    gram
    0.75
    ::::::::
    0.74
    enda
    0.74
    Runtime
    0.73
    Activations Density 0.019%

    No Known Activations