© 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. 30083
    Prev
    Next
    INDEX
    Explanations

    instances of keys or identifiers within a programming context

    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
    156
    +0.12
    0.7%
    450
    +0.10
    0.6%
    195
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.12
    0.03
    57
    +0.10
    0.02
    379
    +0.10
    0.03
    Negative Logits
    Ļª
    -2.01
    ·
    -1.95
    IJ
    -1.86
    ·¸
    -1.78
    ³
    -1.76
    Ĩ
    -1.74
    Ĭ
    -1.66
    ¿½
    -1.58
    ↵↵
    -1.57
    -1.57
    POSITIVE LOGITS
    stro
    2.11
    stroke
    2.07
    pad
    1.99
    codes
    1.81
    ños
    1.80
    bind
    1.77
    quarters
    1.72
    holder
    1.71
    buk
    1.71
    chains
    1.71
    Activations Density 0.060%

    No Known Activations