© 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. 8748
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting characters that separate elements or indicate structure in the text

    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
    21
    +0.13
    0.7%
    296
    +0.12
    0.7%
    122
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.13
    0.03
    408
    +0.12
    0.03
    21
    +0.11
    0.01
    Negative Logits
     Secondly
    -1.46
    mma
    -1.41
    ouin
    -1.35
    issance
    -1.30
     Lions
    -1.29
    rost
    -1.27
     Year
    -1.24
     était
    -1.22
    ffen
    -1.22
     (,
    -1.22
    POSITIVE LOGITS
     third
    1.98
    3
    1.87
     3
    1.80
    ylvania
    1.80
     Third
    1.75
    iders
    1.62
    Ķ
    1.57
    third
    1.52
     fibrillation
    1.50
    à³
    1.44
    Activations Density 0.402%

    No Known Activations