© 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. 4-RES-SM
    11. 8753
    Prev
    Next
    INDEX
    Explanations

    references to specific cellular mechanisms and functions in cancer research

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    226
    +0.14
    0.8%
    321
    +0.13
    0.7%
    81
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.14
    0.03
    226
    +0.13
    0.03
    240
    +0.13
    0.00
    Negative Logits
     Edison
    -1.98
     gallon
    -1.73
     solids
    -1.73
     bearings
    -1.55
     locality
    -1.55
     Schwe
    -1.55
    Willi
    -1.53
     Schmidt
    -1.52
     basin
    -1.49
    ielder
    -1.48
    POSITIVE LOGITS
     miR
    2.66
     apoptotic
    2.59
     siRNA
    2.49
    ¤
    2.48
    ¹
    2.47
     apoptosis
    2.45
     miRNA
    2.39
     downregulated
    2.38
    Ĩ
    2.30
    Ģ
    2.29
    Activations Density 0.209%

    No Known Activations