© 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. 8698
    Prev
    Next
    INDEX
    Explanations

    mentions of different models and modeling processes

    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
    286
    +0.12
    0.7%
    71
    +0.12
    0.7%
    14
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.01
    189
    +0.12
    0.03
    130
    +0.11
    0.03
    Negative Logits
    ¯
    -3.17
    ¬
    -3.10
    §
    -3.00
    ²
    -2.72
    ¿
    -2.61
    ¤
    -2.55
    ĸ
    -2.46
    ļ
    -2.46
    ¨
    -2.45
    Ĺ
    -2.43
    POSITIVE LOGITS
     organism
    2.16
    ing
    2.07
     predicts
    1.97
    woman
    1.89
    matic
    1.86
     parameters
    1.82
     atmosp
    1.80
    ical
    1.80
     predicting
    1.77
     organisms
    1.75
    Activations Density 0.306%

    No Known Activations