© 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. 13952
    Prev
    Next
    INDEX
    Explanations

    anatomical and physiological references related to the pancreas and digestive system

    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%
    81
    +0.14
    0.9%
    93
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.16
    0.00
    71
    +0.14
    0.06
    156
    +0.13
    0.06
    Negative Logits
    §
    -2.94
    ĥ
    -2.71
    ª
    -2.64
    ĵ
    -2.60
    Ĭ
    -2.57
    Ļ
    -2.55
    ĸ
    -2.49
    ¥
    -2.49
    ©
    -2.46
    ı
    -2.45
    POSITIVE LOGITS
    epid
    1.90
     parench
    1.90
    stem
    1.83
    vast
    1.79
    ect
    1.75
    bone
    1.74
    é«
    1.71
    opan
    1.71
    ascus
    1.68
    plant
    1.67
    Activations Density 0.403%

    No Known Activations