© 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. 9059
    Prev
    Next
    INDEX
    Explanations

    phrases related to Freemasonry

    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
    326
    +0.13
    0.6%
    288
    +0.13
    0.5%
    420
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.11
    326
    +0.13
    0.09
    401
    +0.12
    0.06
    Negative Logits
    draw
    -0.85
    upon
    -0.83
    lihood
    -0.83
    gap
    -0.75
     Paula
    -0.72
    ãĥij
    -0.69
    stage
    -0.69
    PsyNetMessage
    -0.68
     Pigs
    -0.68
    sweet
    -0.68
    POSITIVE LOGITS
    asonic
    1.27
    asonry
    1.06
    asons
    0.99
    imore
    0.98
    ry
    0.98
    ocene
    0.95
    ety
    0.95
    uth
    0.94
    ason
    0.91
     Lodge
    0.90
    Activations Density 1.170%

    No Known Activations