© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    references to military technology and aerospace advancements

    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
    156
    +0.16
    0.9%
    21
    +0.13
    0.8%
    12
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    405
    +0.16
    0.05
    159
    +0.13
    0.11
    360
    +0.13
    0.09
    Negative Logits
    ĻĤ
    -2.22
    ¢
    -2.19
    ľĵ
    -2.06
    Į
    -2.00
    ²
    -1.95
     remar
    -1.94
    ãĤĥ
    -1.92
     divorce
    -1.91
    uria
    -1.88
    ī
    -1.85
    POSITIVE LOGITS
     drone
    3.16
     drones
    3.11
     missiles
    2.97
     helicopter
    2.90
     helicopters
    2.87
     aircraft
    2.87
     spacecraft
    2.75
     rockets
    2.73
     missile
    2.70
     payload
    2.61
    Activations Density 2.771%

    No Known Activations