© 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. 27079
    Prev
    Next
    INDEX
    Explanations

    dates and numerical data related to medical studies and hospital settings

    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
    418
    +0.15
    0.8%
    98
    +0.13
    0.7%
    134
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.15
    0.07
    418
    +0.13
    -0.01
    340
    +0.11
    0.04
    Negative Logits
     offensive
    -1.82
     hash
    -1.71
     upside
    -1.69
     “
    -1.66
     enemy
    -1.58
     ‘
    -1.56
     peaceful
    -1.55
     weapons
    -1.55
     mash
    -1.53
     enemies
    -1.53
    POSITIVE LOGITS
    ĻĤ
    3.09
    ±
    3.05
    ij
    3.05
    ĸ´
    2.99
    ³
    2.96
    č↵
    2.94
    ↵
    2.94
    ↵
    2.94
    2.94
    ↵
    2.94
    Activations Density 0.606%

    No Known Activations