© 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. 24150
    Prev
    Next
    INDEX
    Explanations

    references to membership in various organizations or communities

    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
    +0.16
    0.9%
    457
    +0.11
    0.6%
    379
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.16
    0.03
    4
    +0.11
    0.02
    343
    +0.11
    0.03
    Negative Logits
    ¢
    -3.12
    Ļª
    -3.03
    -2.88
    ↵↵↵
    -2.88
    -2.88
    č↵
    -2.88
    -2.88
    ↵
    -2.88
    ↵↵
    -2.88
     ↵
    -2.88
    POSITIVE LOGITS
    hood
    1.83
    classes
    1.82
    iets
    1.78
    liest
    1.73
    hir
    1.71
    quarters
    1.71
     quarters
    1.71
    ials
    1.64
    atics
    1.63
    gio
    1.63
    Activations Density 0.090%

    No Known Activations