© 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 EvalsExportsAPI 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. 12760
    Prev
    Next
    INDEX
    Explanations

    financial terms and data points related to rates, pricing, and market fluctuations

    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
    370
    +0.14
    0.8%
    443
    +0.14
    0.8%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.02
    11
    +0.14
    0.05
    484
    +0.12
    0.01
    Negative Logits
    letons
    -1.75
    ¼
    -1.69
    ych
    -1.69
    olog
    -1.55
    Shell
    -1.49
    аÑģÑĤ
    -1.47
     Armenian
    -1.43
    ÅĦ
    -1.43
    iscopal
    -1.42
    aml
    -1.42
    POSITIVE LOGITS
     Rate
    3.51
     rate
    3.33
    Rate
    3.29
     rates
    3.22
     Rates
    3.02
    rates
    2.82
    rate
    2.78
    RATE
    2.27
     Ratio
    2.00
     mortality
    1.98
    Activations Density 1.198%

    No Known Activations