© 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. 30036
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or court-related terms

    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
    434
    +0.15
    0.9%
    129
    +0.12
    0.7%
    271
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    434
    +0.15
    0.02
    89
    +0.12
    0.01
    211
    +0.11
    0.01
    Negative Logits
    ?’
    -1.92
    ?",
    -1.86
     '%
    -1.75
    )',
    -1.73
    ?”
    -1.71
    ?'
    -1.70
    ...'
    -1.60
    )",
    -1.59
     millenn
    -1.58
    ?!
    -1.54
    POSITIVE LOGITS
    ·
    3.98
    ©
    3.95
    ´
    3.82
    ¶
    3.77
      ↵
    3.74
    ↵↵
    3.74
    ↵            ↵
    3.74
    3.74
    č↵
    3.74
    3.74
    Activations Density 0.074%

    No Known Activations