© 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. 29931
    Prev
    Next
    INDEX
    Explanations

    elements related to notifications and string manipulations in programming 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/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
    269
    +0.18
    1.0%
    365
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.18
    0.02
    155
    +0.14
    0.02
    379
    +0.12
    0.02
    Negative Logits
    hire
    -1.59
    abouts
    -1.52
    ductive
    -1.49
    ”?
    -1.48
     developing
    -1.47
    duct
    -1.44
    "?
    -1.43
    jun
    -1.43
    hip
    -1.42
     synergistic
    -1.41
    POSITIVE LOGITS
    Ĵ
    2.40
    ĨĴ
    2.30
    İ
    2.29
    ģ
    2.16
    ±
    2.15
    ĩ
    2.09
    Ļ
    2.09
    ¢
    2.04
    £
    2.03
    ¡
    2.03
    Activations Density 0.084%

    No Known Activations