© 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. 1-RES-SM
    11. 26120
    Prev
    Next
    INDEX
    Explanations

    references to financial costs and expenses

    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
    365
    +0.15
    0.9%
    156
    +0.15
    0.9%
    178
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.15
    0.06
    141
    +0.15
    0.04
    365
    +0.14
    0.04
    Negative Logits
    ¿½
    -3.91
    Ĵ
    -3.79
    ĥ½
    -3.73
      ↵
    -3.47
    -3.47
                ↵
    -3.47
    <|padding|>
    -3.47
    -3.47
    ↵
    -3.47
    -3.47
    POSITIVE LOGITS
    heet
    2.13
    hell
    2.07
    ume
    1.93
    mith
    1.73
    urance
    1.72
     incurred
    1.70
     are
    1.66
    orbent
    1.66
    uits
    1.59
    icum
    1.59
    Activations Density 0.319%

    No Known Activations