© 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. 10157
    Prev
    Next
    INDEX
    Explanations

    names of national parks and historical sites

    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
    442
    +0.15
    0.5%
    569
    +0.14
    0.4%
    174
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.15
    0.06
    404
    +0.14
    0.05
    99
    +0.14
    0.04
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -1.29
    ĸļ
    -1.06
     warr
    -1.00
     Colt
    -0.99
    DragonMagazine
    -0.99
    different
    -0.97
     Tanz
    -0.96
     Parenthood
    -0.96
     TAM
    -0.96
     convol
    -0.96
    POSITIVE LOGITS
    otine
    1.61
    entric
    1.50
    illin
    1.47
    henko
    1.41
    ornia
    1.39
    chio
    1.37
    inity
    1.36
    otic
    1.29
    oplan
    1.28
    ourt
    1.28
    Activations Density 0.910%

    No Known Activations