© 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. 8903
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of towns and geographical locations

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    477
    +0.14
    0.8%
    216
    +0.13
    0.7%
    326
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.14
    0.09
    432
    +0.13
    0.08
    216
    +0.12
    0.09
    Negative Logits
    Ĥ
    -5.31
    Īĺ
    -5.22
    Ļ
    -5.20
    ĭ
    -5.08
    Ĥ¬
    -5.06
    ¦
    -5.04
    ¯
    -5.01
    Ľ
    -4.95
    ĥ½
    -4.94
    ī
    -4.93
    POSITIVE LOGITS
    shire
    3.86
     County
    3.74
     Township
    3.33
     Heights
    2.91
    town
    2.68
    County
    2.67
    burg
    2.60
     COUNTY
    2.59
     Hills
    2.55
     county
    2.55
    Activations Density 0.578%

    No Known Activations