© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2078
    Prev
    Next
    INDEX
    Explanations

    information related to the aviation and aerospace industries

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.15
    1.0%
    575
    +0.07
    0.5%
    464
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.09
    575
    +0.07
    0.06
    57
    +0.07
    0.04
    Negative Logits
    ifier
    -0.56
    orah
    -0.54
    ga
    -0.54
    payer
    -0.53
    ilts
    -0.52
    bos
    -0.52
    utsche
    -0.51
    chery
    -0.50
    ":""},{"
    -0.50
    itzer
    -0.49
    POSITIVE LOGITS
     engineering
    0.55
     industry
    0.53
     accidents
    0.52
    querque
    0.51
     jargon
    0.51
     Industry
    0.51
     pursuits
    0.51
    ufact
    0.49
     peripher
    0.49
     terminology
    0.48
    Activations Density 0.487%

    No Known Activations