© 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. 23952
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and export statements

    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
    353
    +0.13
    0.7%
    455
    +0.12
    0.7%
    297
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.13
    0.03
    455
    +0.12
    0.02
    12
    +0.12
    0.01
    Negative Logits
    ophyll
    -1.75
    hoe
    -1.72
    ichlet
    -1.71
    java
    -1.71
    ador
    -1.64
    worm
    -1.64
    gnu
    -1.57
    illus
    -1.57
    hydrogen
    -1.55
    compute
    -1.55
    POSITIVE LOGITS
    ĥ
    2.36
    ¥
    2.30
    ³
    2.30
    ·
    2.21
    ª
    2.20
    Ļª
    2.15
    Ĺ
    2.14
    ¦
    2.11
    ↵
    2.09
    2.09
    Activations Density 0.258%

    No Known Activations