© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13430
    Prev
    Next
    INDEX
    Explanations

    terms related to drugs and drug usage

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.1%
    453
    +0.13
    0.8%
    42
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.18
    0.03
    495
    +0.13
    0.02
    186
    +0.12
    0.02
    Negative Logits
     parentheses
    -1.79
     certain
    -1.75
    TRODUCTION
    -1.67
     biblical
    -1.67
    GREEK
    -1.66
    orkshire
    -1.63
    ahoma
    -1.61
     notions
    -1.61
     realize
    -1.60
     sermon
    -1.54
    POSITIVE LOGITS
    icide
    2.04
    maker
    1.90
    makers
    1.88
    ¹
    1.81
    fight
    1.77
    ulent
    1.77
    icides
    1.77
    store
    1.71
    ²
    1.69
    ulence
    1.69
    Activations Density 0.069%

    No Known Activations