© 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. 25522
    Prev
    Next
    INDEX
    Explanations

    technical explanations related to biochemical processes and molecular interactions

    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
    47
    +0.21
    1.2%
    23
    +0.21
    1.2%
    156
    +0.20
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.21
    0.09
    156
    +0.21
    0.09
    7
    +0.20
    0.05
    Negative Logits
    rieved
    -1.74
     charts
    -1.61
     dated
    -1.56
     listings
    -1.50
    érie
    -1.50
    tab
    -1.49
     recommendations
    -1.49
    SEE
    -1.47
    ruary
    -1.47
     ratings
    -1.47
    POSITIVE LOGITS
    ¯
    2.59
    ij
    2.59
    ¿½
    2.55
    £
    2.48
    ↵
    2.45
    ↵
    2.45
    ↵↵
    2.45
       ↵
    2.45
    ↵↵
    2.45
    2.45
    Activations Density 1.189%

    No Known Activations