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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29718
    Prev
    Next
    INDEX
    Explanations

    references to antibiotics and their usage in medical contexts

    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
    +0.16
    0.9%
    320
    +0.15
    0.9%
    158
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.16
    0.02
    186
    +0.15
    0.01
    495
    +0.13
    0.01
    Negative Logits
    ĺ
    -1.95
    ±
    -1.84
     où
    -1.69
    ı
    -1.67
    amed
    -1.66
    ©
    -1.65
    aliana
    -1.63
     Mathemat
    -1.62
    how
    -1.56
    ļ
    -1.52
    POSITIVE LOGITS
    icillin
    2.31
     prophylaxis
    1.85
    oxacin
    1.77
    acycline
    1.59
     antibiotics
    1.55
     steward
    1.52
    resistant
    1.52
     resistant
    1.52
     antibiotic
    1.49
     antifungal
    1.48
    Activations Density 0.092%

    No Known Activations