© 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. 25509
    Prev
    Next
    INDEX
    Explanations

    mentions of age, particularly focusing on "age 9" and its relation to various health metrics

    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
    358
    +0.15
    0.8%
    290
    +0.13
    0.7%
    51
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    358
    +0.15
    0.04
    290
    +0.13
    0.03
    213
    +0.13
    0.02
    Negative Logits
     else
    -1.80
     vengeance
    -1.56
    uscular
    -1.56
    pton
    -1.49
    iqu
    -1.46
     faith
    -1.41
    >'
    -1.41
    nah
    -1.39
    ,'"
    -1.37
    mys
    -1.36
    POSITIVE LOGITS
     adjustment
    1.75
     stratification
    1.51
     gradient
    1.51
     optimum
    1.51
     registration
    1.50
    ster
    1.47
     adaptation
    1.46
    picker
    1.43
    **:
    1.40
    ward
    1.40
    Activations Density 0.085%

    No Known Activations