© 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. 1-RES-SM
    11. 30045
    Prev
    Next
    INDEX
    Explanations

    specific variable names and types in programming-related text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    462
    +0.14
    0.8%
    108
    +0.12
    0.7%
    89
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.14
    0.00
    249
    +0.12
    0.00
    369
    +0.12
    0.00
    Negative Logits
    Ģ
    -3.68
    ¹
    -3.63
    ¥
    -3.56
    Ħ
    -3.55
    ĸ´
    -3.50
    ª
    -3.50
    ¶
    -3.47
    Ī
    -3.47
    ĩ
    -3.43
    ²
    -3.38
    POSITIVE LOGITS
    [@
    1.55
     founded
    1.53
     onward
    1.44
    ism
    1.43
    ert
    1.42
     nationwide
    1.42
    ides
    1.41
     today
    1.38
    \[[@
    1.36
     behold
    1.34
    Activations Density 0.000%

    No Known Activations