© 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. 1-RES-SM
    11. 24612
    Prev
    Next
    INDEX
    Explanations

    mentions of specific characters or terms related to bacteria and incidents

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.17
    1.0%
    397
    +0.13
    0.8%
    370
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.04
    271
    +0.13
    0.01
    156
    +0.13
    0.03
    Negative Logits
     sure
    -1.77
    >`
    -1.74
     ?>
    -1.54
    '?"
    -1.48
     promise
    -1.48
    rangle
    -1.46
    oving
    -1.43
     talk
    -1.41
     teach
    -1.40
    coming
    -1.39
    POSITIVE LOGITS
     pylori
    2.48
    naire
    2.04
    enstein
    1.71
    esan
    1.68
    obacterium
    1.66
    rico
    1.64
    ians
    1.63
    Åij
    1.63
    rique
    1.62
    ocide
    1.59
    Activations Density 0.075%

    No Known Activations