© 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. 24123
    Prev
    Next
    INDEX
    Explanations

    terms related to indexing within data structures or collections

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.19
    1.1%
    413
    +0.13
    0.8%
    249
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    413
    +0.19
    0.02
    129
    +0.13
    0.01
    224
    +0.13
    0.03
    Negative Logits
    rin
    -1.73
     clean
    -1.71
     transparent
    -1.57
     wide
    -1.52
     blue
    -1.50
    ¿½
    -1.44
     unnatural
    -1.44
    ly
    -1.42
     jelly
    -1.42
     ever
    -1.42
    POSITIVE LOGITS
    emen
    1.78
    aho
    1.69
    enburg
    1.68
    ición
    1.67
    es
    1.65
    ionale
    1.63
     Strateg
    1.60
    Club
    1.60
    isters
    1.59
    ÃŃf
    1.57
    Activations Density 0.324%

    No Known Activations