© 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 Local
    9. 6-RES_SCL-AJT
    11. 37065
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms, such as names of diseases, research methods, and biological processes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.29
    1.4%
    267
    +0.11
    0.5%
    260
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.29
    0.14
    393
    +0.11
    0.27
    45
    +0.10
    0.04
    Negative Logits
    gur
    -0.81
    iche
    -0.70
    coe
    -0.68
    ansas
    -0.64
    side
    -0.63
    tesy
    -0.62
    des
    -0.61
    pour
    -0.61
    estate
    -0.61
    lees
    -0.61
    POSITIVE LOGITS
     correlations
    0.86
     abnormalities
    0.82
     heterogeneity
    0.79
     probable
    0.78
     variability
    0.73
     unequivocally
    0.70
     convinc
    0.70
     correlation
    0.69
     significant
    0.69
     discrepancies
    0.68
    Activations Density 12.580%

    No Known Activations