© 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. 28974
    Prev
    Next
    INDEX
    Explanations

    data related to interest rates

    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
    2
    +0.16
    0.9%
    477
    +0.12
    0.7%
    437
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.16
    0.04
    2
    +0.12
    0.03
    500
    +0.12
    0.03
    Negative Logits
    IJ
    -2.23
    İ
    -2.10
    ¤
    -2.02
    ½
    -2.00
    ±
    -1.99
    ľĵ
    -1.97
    ¸
    -1.96
    ª
    -1.91
    ĥ½
    -1.85
    Īĺ
    -1.81
    POSITIVE LOGITS
     rates
    1.87
    ÅĽÄĩ
    1.79
    ball
    1.76
    balls
    1.70
    etable
    1.69
    limiting
    1.62
     rate
    1.58
     card
    1.56
    igt
    1.54
    az
    1.53
    Activations Density 0.095%

    No Known Activations