© 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. 24139
    Prev
    Next
    INDEX
    Explanations

    references to various countries

    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
    +0.17
    1.0%
    52
    +0.12
    0.7%
    168
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.17
    0.07
    321
    +0.12
    0.06
    52
    +0.12
    0.05
    Negative Logits
    ¾
    -3.46
    ¼
    -3.37
    ¹
    -3.31
    ¶
    -3.29
    ±
    -3.22
    Ħ
    -3.20
    ĥ½
    -3.13
    ´
    -3.09
    č↵
    -3.04
    ↵
    -3.04
    POSITIVE LOGITS
     Today
    1.91
    borg
    1.78
    ICO
    1.66
     itself
    1.60
    sheet
    1.55
    ico
    1.54
     Clerk
    1.49
    iral
    1.49
     Sheet
    1.40
     sheet
    1.37
    Activations Density 0.289%

    No Known Activations