© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10743
    Prev
    Next
    INDEX
    Explanations

    terms related to health prevention strategies and epidemiology

    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
    459
    +0.13
    0.7%
    156
    +0.12
    0.7%
    486
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.13
    0.00
    186
    +0.12
    0.02
    38
    +0.12
    0.01
    Negative Logits
    ĻĤ
    -2.81
    »¿
    -2.72
    ĥ½
    -2.62
    Īĺ
    -2.61
    ©
    -2.58
    ½
    -2.44
    ĺ
    -2.44
    Ĵ
    -2.38
    ģ
    -2.38
    £
    -2.37
    POSITIVE LOGITS
     programmes
    1.96
     campaigns
    1.86
     measures
    1.77
     programme
    1.77
    ulent
    1.75
     choice
    1.73
    ancial
    1.67
     prevention
    1.60
    iator
    1.59
    ctive
    1.56
    Activations Density 0.204%

    No Known Activations