© 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. 27517
    Prev
    Next
    INDEX
    Explanations

    terms related to HIV and other viral infections

    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
    +0.32
    2.0%
    397
    +0.15
    0.9%
    410
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.32
    0.01
    304
    +0.15
    0.01
    333
    +0.13
    0.01
    Negative Logits
     hers
    -1.65
     vagu
    -1.64
     fois
    -1.63
     unanimous
    -1.63
    -1.61
    ↵↵
    -1.61
    ↵↵
    -1.61
    <|outofrange|>
    -1.61
    ↵
    -1.61
    ↵
    -1.61
    POSITIVE LOGITS
    ILITY
    2.01
    iral
    1.83
    NG
    1.80
    ISM
    1.78
    IV
    1.76
    ESE
    1.75
    ulent
    1.69
    STAT
    1.66
    VD
    1.62
     dehydrogenase
    1.56
    Activations Density 0.055%

    No Known Activations