© 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. 9574
    Prev
    Next
    INDEX
    Explanations

    references to political or governmental topics

    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
    446
    +0.12
    0.6%
    175
    +0.11
    0.6%
    195
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.12
    0.03
    175
    +0.11
    0.03
    501
    +0.10
    0.02
    Negative Logits
    ecal
    -1.67
    UNC
    -1.63
    '>
    -1.57
    inos
    -1.56
    apple
    -1.53
    onomous
    -1.52
    incial
    -1.51
    oshi
    -1.50
    """
    -1.46
    inct
    -1.45
    POSITIVE LOGITS
    ¢
    2.02
    º
    1.93
     gegen
    1.93
    recht
    1.93
     für
    1.91
     bes
    1.87
    IJ
    1.87
     zur
    1.86
     auf
    1.85
     mö
    1.83
    Activations Density 0.360%

    No Known Activations