© 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. 2-RES-SM
    11. 27879
    Prev
    Next
    INDEX
    Explanations

    references to specific years and notable political figures

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    471
    +0.14
    0.8%
    71
    +0.13
    0.7%
    266
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.14
    0.03
    133
    +0.13
    0.02
    253
    +0.12
    0.02
    Negative Logits
     recent
    -1.72
    ages
    -1.50
     sizes
    -1.49
     hers
    -1.48
    iness
    -1.47
     tonight
    -1.47
     aside
    -1.46
     spice
    -1.46
     today
    -1.45
     corners
    -1.42
    POSITIVE LOGITS
    nai
    1.62
    ERN
    1.59
    ska
    1.54
    erals
    1.49
     onwards
    1.48
    PHA
    1.47
     год
    1.47
    liament
    1.47
    onaut
    1.45
    à¯ģ
    1.45
    Activations Density 0.054%

    No Known Activations