© 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. 2-RES-SM
    11. 10393
    Prev
    Next
    INDEX
    Explanations

    references to health-related data and statistics in various contexts

    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
    47
    +0.13
    0.7%
    156
    +0.12
    0.7%
    45
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.13
    0.01
    35
    +0.12
    -0.02
    485
    +0.11
    0.04
    Negative Logits
     Stadium
    -1.53
     ;
    -1.46
    upgreek
    -1.45
    iday
    -1.40
    gh
    -1.34
    buntu
    -1.32
    FUN
    -1.31
     $.
    -1.31
    .);
    -1.31
    sted
    -1.30
    POSITIVE LOGITS
    ·¸
    2.17
     {#
    1.90
     alike
    1.67
    Ļª
    1.67
    č↵
    1.66
    ↵            ↵
    1.66
    č↵
    1.66
    1.66
    č↵
    1.66
     ↵
    1.66
    Activations Density 4.822%

    No Known Activations