© 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. 2-RES-SM
    11. 26152
    Prev
    Next
    INDEX
    Explanations

    constructs and concepts within programming and software engineering contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.1%
    63
    +0.16
    0.9%
    400
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.18
    0.07
    63
    +0.16
    0.07
    400
    +0.12
    0.02
    Negative Logits
    Decided
    -1.63
     CIRCUIT
    -1.56
     ensued
    -1.52
    veis
    -1.49
    ãĤī
    -1.48
    uscript
    -1.48
    arxiv
    -1.41
    ramento
    -1.41
    ****************************************************************************
    -1.35
    doibase
    -1.34
    POSITIVE LOGITS
    ¿½
    1.71
    į
    1.68
    ļ
    1.66
    §
    1.60
    IJ
    1.59
    ¢
    1.58
    ħ
    1.57
    ↵  Âł
    1.53
              ↵
    1.53
    1.53
    Activations Density 8.037%

    No Known Activations