© 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. 25536
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    492
    +0.16
    0.9%
    478
    +0.16
    0.9%
    510
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.16
    0.01
    346
    +0.16
    0.01
    510
    +0.13
    0.01
    Negative Logits
     condition
    -1.60
     conditions
    -1.52
    ement
    -1.48
     parameters
    -1.47
    pad
    -1.42
     :=
    -1.35
    Ļª
    -1.34
     components
    -1.33
     equip
    -1.32
    enium
    -1.32
    POSITIVE LOGITS
    unnumbered
    1.80
     dece
    1.54
    theless
    1.52
    boro
    1.43
    mares
    1.42
     Dreams
    1.39
    ifies
    1.38
     Arabia
    1.37
     tears
    1.33
    reve
    1.28
    Activations Density 0.042%

    No Known Activations