© 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. 25959
    Prev
    Next
    INDEX
    Explanations

    references to mothers and maternal 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/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
    410
    +0.14
    0.8%
    328
    +0.12
    0.7%
    93
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.14
    0.04
    87
    +0.12
    0.03
    469
    +0.11
    0.03
    Negative Logits
    amen
    -1.48
     Latin
    -1.46
    verted
    -1.44
    unes
    -1.42
    hed
    -1.42
    FTWARE
    -1.39
     others
    -1.37
     transmembrane
    -1.36
    >';
    -1.36
    ype
    -1.34
    POSITIVE LOGITS
    hood
    2.46
    boards
    1.91
    ding
    1.91
    hesis
    1.80
    stown
    1.79
    heses
    1.78
    ila
    1.69
    ship
    1.61
    holm
    1.58
    ande
    1.56
    Activations Density 0.073%

    No Known Activations