© 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. 30068
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to property and rights

    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
    23
    +0.30
    1.8%
    50
    +0.15
    0.9%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.30
    0.19
    8
    +0.15
    0.09
    485
    +0.13
    0.07
    Negative Logits
    İ
    -1.74
    eme
    -1.64
    plots
    -1.59
    folio
    -1.58
    emos
    -1.56
    ®
    -1.56
     yourselves
    -1.54
    ableness
    -1.54
     believes
    -1.54
     brings
    -1.54
    POSITIVE LOGITS
     slower
    1.58
     respectively
    1.56
      ↵
    1.53
     crap
    1.52
    ↵
    1.51
     better
    1.48
     complete
    1.47
     hell
    1.46
     <!--
    1.41
    1.40
    Activations Density 2.437%

    No Known Activations