© 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. 23826
    Prev
    Next
    INDEX
    Explanations

    references to developers and their roles in software and application creation

    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
    +0.28
    1.7%
    365
    +0.17
    1.0%
    119
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.28
    0.03
    405
    +0.17
    0.02
    119
    +0.16
    0.02
    Negative Logits
    von
    -1.53
    ede
    -1.48
     COURT
    -1.42
      ↵
    -1.40
     carotid
    -1.39
    ÑĶ
    -1.38
     Breast
    -1.36
     vaginal
    -1.32
     previous
    -1.32
    ÑĢа
    -1.32
    POSITIVE LOGITS
    gery
    1.91
     projects
    1.81
    pieces
    1.80
    liness
    1.66
    zilla
    1.64
     supplies
    1.61
     behind
    1.58
    utions
    1.55
     mistakes
    1.50
     touches
    1.50
    Activations Density 0.126%

    No Known Activations