© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24054
    Prev
    Next
    INDEX
    Explanations

    terms associated with memory allocation and management in programming

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.13
    0.7%
    252
    +0.13
    0.7%
    162
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.13
    0.03
    86
    +0.13
    0.02
    111
    +0.12
    0.03
    Negative Logits
    Ĥ¬
    -3.01
    ¹
    -2.78
    Ĥ
    -2.60
    ©
    -2.53
    ĨĴ
    -2.52
    Ļª
    -2.49
    ¾
    -2.43
    ¿
    -2.42
    ↵
    -2.33
    ↵
    -2.33
    POSITIVE LOGITS
    entric
    2.12
    ution
    1.70
    rition
    1.57
    igated
    1.55
    ortex
    1.50
    igator
    1.48
    vering
    1.48
     control
    1.37
     recall
    1.36
    ortical
    1.34
    Activations Density 0.305%

    No Known Activations