© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    actions related to community service and helping others

    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
    764
    +0.16
    0.6%
    521
    +0.16
    0.6%
    69
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.16
    0.03
    31
    +0.16
    0.03
    257
    +0.12
    0.03
    Negative Logits
    paces
    -0.89
     Mellon
    -0.85
    lished
    -0.85
    hop
    -0.83
    arthy
    -0.80
     appell
    -0.80
    perty
    -0.79
    é¾į
    -0.77
     Curve
    -0.76
     tom
    -0.76
    POSITIVE LOGITS
    rive
    0.98
     Cancel
    0.98
    scription
    0.93
    su
    0.90
    Crime
    0.86
    psc
    0.85
     embed
    0.80
    gement
    0.80
    icia
    0.79
     typing
    0.78
    Activations Density 0.178%

    No Known Activations