© 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. 25090
    Prev
    Next
    INDEX
    Explanations

    dates and numerical references related to historical events

    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
    490
    +0.13
    0.7%
    476
    +0.11
    0.6%
    97
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.13
    0.04
    51
    +0.11
    0.04
    475
    +0.10
    0.04
    Negative Logits
    Į
    -3.91
    ĻĤ
    -3.88
    «
    -3.69
    ©
    -3.66
    ³
    -3.66
    ¿
    -3.62
    ¼
    -3.57
    ·¸
    -3.56
    ¹
    -3.50
    ²
    -3.50
    POSITIVE LOGITS
    ^(
    1.84
     recipients
    1.67
    80211
    1.64
    hti
    1.52
    ères
    1.48
    ^[
    1.48
    MPL
    1.45
    iors
    1.44
    gio
    1.42
    ram
    1.42
    Activations Density 0.173%

    No Known Activations