© 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. 23799
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to hallucinogenic substances and cannabinoids

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    494
    +0.14
    0.8%
    470
    +0.13
    0.7%
    400
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.14
    0.03
    79
    +0.13
    0.02
    322
    +0.12
    0.02
    Negative Logits
    Ļª
    -1.94
    ŀ
    -1.77
    iles
    -1.59
     huge
    -1.57
     charts
    -1.53
     mates
    -1.48
    OTT
    -1.47
    ĭ
    -1.47
    board
    -1.45
    ı
    -1.44
    POSITIVE LOGITS
    atories
    1.77
    stim
    1.73
    esis
    1.69
    eration
    1.63
    factory
    1.59
    remia
    1.59
    estamp
    1.57
    ocide
    1.56
    ação
    1.56
    ste
    1.54
    Activations Density 0.453%

    No Known Activations