© 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. 37226
    Prev
    Next
    INDEX
    Explanations

    articles in newspapers

    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
    +0.20
    0.9%
    336
    +0.13
    0.6%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.05
    235
    +0.13
    0.10
    336
    +0.12
    0.04
    Negative Logits
    ayne
    -0.90
    imilar
    -0.85
    fee
    -0.84
    paren
    -0.81
    orsi
    -0.77
    reek
    -0.76
    alli
    -0.75
    adow
    -0.75
    othal
    -0.75
    adders
    -0.73
    POSITIVE LOGITS
     columnist
    1.00
    lisher
    0.94
     publisher
    0.91
     editor
    0.90
     advertis
    0.87
     articles
    0.87
     archives
    0.86
     publishers
    0.86
     editors
    0.86
     newspapers
    0.86
    Activations Density 9.754%

    No Known Activations