© 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. 4-RES-SM
    11. 9368
    Prev
    Next
    INDEX
    Explanations

    terms related to economic conditions and their effects

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    70
    +0.15
    0.8%
    501
    +0.13
    0.7%
    395
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.15
    0.03
    11
    +0.13
    0.03
    70
    +0.12
    0.04
    Negative Logits
    ureus
    -1.68
    ows
    -1.63
    ering
    -1.61
    avir
    -1.59
    اÛĮ
    -1.56
    arers
    -1.55
    eric
    -1.55
    iki
    -1.53
    ubert
    -1.52
    dered
    -1.48
    POSITIVE LOGITS
     climate
    2.24
     affairs
    1.99
     implications
    1.98
     incentives
    1.97
     consequences
    1.93
     forecast
    1.85
     forecasts
    1.85
     hardship
    1.83
     benefits
    1.81
     conditions
    1.80
    Activations Density 0.162%

    No Known Activations