© 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. 23857
    Prev
    Next
    INDEX
    Explanations

    references to various types of agencies and bureaucracies

    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
    +0.24
    1.4%
    365
    +0.14
    0.8%
    219
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.24
    0.11
    156
    +0.14
    0.07
    271
    +0.11
    0.05
    Negative Logits
     aloud
    -1.79
     ago
    -1.72
    abouts
    -1.72
     generations
    -1.71
    teenth
    -1.68
     earlier
    -1.67
     Orthodox
    -1.66
     dissent
    -1.66
     eternity
    -1.53
     spoken
    -1.53
    POSITIVE LOGITS
    »¿
    2.08
    °
    1.99
    ·
    1.95
    ¾
    1.83
    ģ
    1.82
    mozilla
    1.80
    ¸
    1.76
    ¥
    1.75
    ICE
    1.69
    Ľ
    1.68
    Activations Density 0.488%

    No Known Activations