© 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. MLP Post
    9. 2-MLP-SM
    11. 24272
    Prev
    Next
    INDEX
    Explanations

    quantitative evaluations or measurements related to bacterial counts or infections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    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
    238
    +0.13
    0.8%
    88
    +0.10
    0.6%
    405
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.13
    0.03
    182
    +0.10
    0.03
    189
    +0.09
    0.03
    Negative Logits
    ^[@
    -1.75
    ]{.
    -1.61
    acles
    -1.58
    igu
    -1.57
    }}$$
    -1.54
    |$.
    -1.52
    ality
    -1.52
    aning
    -1.52
    CK
    -1.47
     ]{}
    -1.46
    POSITIVE LOGITS
    ÃŃa
    1.69
    usiness
    1.67
    heet
    1.67
    freak
    1.63
     RPG
    1.57
     ingredient
    1.57
    rowave
    1.56
    wegian
    1.55
    rooms
    1.53
    lists
    1.53
    Activations Density 0.128%

    No Known Activations