© 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. 24014
    Prev
    Next
    INDEX
    Explanations

    references to biological sample collections and analyses

    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
    +0.29
    1.7%
    376
    +0.13
    0.8%
    287
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.29
    0.02
    287
    +0.13
    0.01
    58
    +0.12
    0.01
    Negative Logits
    §
    -4.62
    ŀ
    -4.36
    ĥ½
    -4.32
    ĵ
    -4.30
    Ĵ
    -4.08
    ↵
    -3.97
    <|outofrange|>
    -3.97
    -3.97
          ↵
    -3.97
    -3.97
    POSITIVE LOGITS
    creen
    2.05
    hell
    1.75
     namely
    1.70
     obtained
    1.70
     collected
    1.65
     comprising
    1.62
     among
    1.59
     revealed
    1.57
    ome
    1.55
    heet
    1.54
    Activations Density 0.058%

    No Known Activations