© 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. 28936
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to equations and solutions

    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
    238
    +0.13
    0.7%
    3
    +0.13
    0.7%
    389
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.13
    0.01
    136
    +0.13
    -0.01
    238
    +0.12
    0.01
    Negative Logits
    Ń
    -3.01
    IJ
    -2.80
    ij
    -2.76
    Ļª
    -2.68
    ®
    -2.63
    Ĭ
    -2.63
    ¬
    -2.61
    §
    -2.50
    Ĥ¬
    -2.48
    ĥ
    -2.47
    POSITIVE LOGITS
     overtime
    1.69
    leftarrow
    1.45
    ighs
    1.45
     advance
    1.41
    chitz
    1.41
    ORM
    1.40
    ---|---
    1.38
    ighed
    1.37
    ERO
    1.36
     beating
    1.33
    Activations Density 0.303%

    No Known Activations