© 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. 10355
    Prev
    Next
    INDEX
    Explanations

    Keywords related to historical facts and cultural artifacts, in particular from ancient civilizations

    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
    103
    +0.08
    0.5%
    206
    +0.06
    0.4%
    164
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.08
    0.06
    288
    +0.06
    0.08
    232
    +0.06
    0.05
    Negative Logits
    matic
    -0.58
    bral
    -0.54
    atory
    -0.53
    bers
    -0.53
    bucks
    -0.52
    tic
    -0.51
     Payton
    -0.49
    verbs
    -0.49
    atories
    -0.49
    PH
    -0.48
    POSITIVE LOGITS
    orse
    0.57
    wcsstore
    0.54
    ĵĺ
    0.54
    anced
    0.49
    aste
    0.47
    ounter
    0.46
     Thrones
    0.46
    inction
    0.46
    urer
    0.45
    ension
    0.43
    Activations Density 0.635%

    No Known Activations