© 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. 29611
    Prev
    Next
    INDEX
    Explanations

    references to the Ruby programming language and its related tools and frameworks

    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
    156
    +0.15
    0.9%
    404
    +0.14
    0.8%
    466
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.02
    71
    +0.14
    0.02
    466
    +0.14
    0.01
    Negative Logits
    opic
    -1.60
     younger
    -1.48
    riel
    -1.48
     pregnant
    -1.45
    orry
    -1.45
    orting
    -1.43
    pping
    -1.42
    idding
    -1.41
     obese
    -1.41
    ages
    -1.41
    POSITIVE LOGITS
    forge
    1.90
    inux
    1.86
    izumab
    1.82
    coin
    1.82
    hammer
    1.82
    mund
    1.72
    enstein
    1.61
    izations
    1.58
    estones
    1.57
    irez
    1.57
    Activations Density 0.108%

    No Known Activations