© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    mentions of shaving, beards, and related terms

    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
    214
    +0.14
    0.6%
    57
    +0.13
    0.6%
    288
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.17
    326
    +0.13
    0.13
    343
    +0.13
    0.09
    Negative Logits
     encour
    -0.81
    EMS
    -0.74
    phis
    -0.73
    etting
    -0.72
    odic
    -0.71
    alez
    -0.71
    Cass
    -0.69
    ologue
    -0.69
    gom
    -0.68
    ship
    -0.66
    POSITIVE LOGITS
     shaving
    0.94
     shave
    0.93
     beard
    0.91
     blades
    0.85
    rette
    0.81
     mustache
    0.80
     trimmed
    0.79
     shaved
    0.76
     razor
    0.76
    utic
    0.73
    Activations Density 2.524%

    No Known Activations