© 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. 14316
    Prev
    Next
    INDEX
    Explanations

    medical terms and descriptions related to injuries and their conditions

    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
    47
    +0.24
    1.4%
    156
    +0.19
    1.1%
    507
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.24
    0.09
    16
    +0.19
    0.05
    148
    +0.14
    0.01
    Negative Logits
     rating
    -1.70
     priority
    -1.67
     agenda
    -1.61
    wise
    -1.60
     criteria
    -1.55
     ranking
    -1.52
     updates
    -1.52
    -%
    -1.46
     maps
    -1.44
     sounding
    -1.43
    POSITIVE LOGITS
    ¼
    4.95
    »¿
    4.46
    ľ
    4.10
    ·¸
    4.03
    ĻĤ
    4.02
    Ļª
    4.01
    »
    3.93
    ³
    3.92
    ĸ´
    3.90
    £
    3.86
    Activations Density 0.848%

    No Known Activations