© 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. 2-RES-SM
    11. 26279
    Prev
    Next
    INDEX
    Explanations

    references to World War I and World War II

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    293
    +0.12
    0.7%
    145
    +0.12
    0.6%
    186
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.12
    0.03
    254
    +0.12
    0.02
    319
    +0.11
    0.02
    Negative Logits
    -2.88
    ↵
    -2.88
              ↵
    -2.88
    čč
    -2.88
       ↵
    -2.88
     ↵
    -2.88
    ↵
    -2.88
    ↵  Âł
    -2.88
    ↵↵
    -2.88
    č↵
    -2.88
    POSITIVE LOGITS
    fare
    1.75
     Civil
    1.55
    istory
    1.53
    ocide
    1.47
     era
    1.43
    acerb
    1.43
    overn
    1.42
    ington
    1.42
     Corps
    1.41
     disasters
    1.39
    Activations Density 0.222%

    No Known Activations