© 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. 4-RES-SM
    11. 15325
    Prev
    Next
    INDEX
    Explanations

    coding-related functions or methods that involve parsing and argument handling

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    448
    +0.16
    0.9%
    357
    +0.16
    0.9%
    466
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.16
    0.04
    47
    +0.16
    0.04
    17
    +0.13
    0.03
    Negative Logits
     HTC
    -1.85
     mattress
    -1.81
     Tub
    -1.80
    HIV
    -1.79
     AIDS
    -1.69
     nude
    -1.69
    oors
    -1.69
     monolayer
    -1.65
    AIDS
    -1.61
     cycling
    -1.61
    POSITIVE LOGITS
     parser
    4.11
     parsing
    3.72
     Parse
    3.62
     Pars
    3.55
    Parser
    3.49
     parse
    3.38
    parser
    3.37
    Ŀ
    3.20
     parsed
    3.20
    Pars
    3.15
    Activations Density 0.652%

    No Known Activations