© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 26137
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to advanced physics concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    47
    +0.24
    1.4%
    240
    +0.15
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.24
    0.08
    413
    +0.15
    0.01
    23
    +0.14
    0.07
    Negative Logits
     checklist
    -2.02
     broch
    -2.00
     format
    -1.86
     edition
    -1.86
     affiliate
    -1.84
    quote
    -1.82
    blogger
    -1.76
     advertisement
    -1.75
    documentation
    -1.74
     newsletter
    -1.74
    POSITIVE LOGITS
    Ļª
    3.25
    IJ
    2.98
    ĸ
    2.95
    Ĺ
    2.85
    ĥ
    2.81
    »¿
    2.81
    Ī
    2.80
    ij
    2.79
    µ
    2.76
    Ŀ
    2.74
    Activations Density 0.818%

    No Known Activations