© 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. 32412
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to orders and shipping

    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
    419
    +0.17
    1.0%
    47
    +0.17
    1.0%
    237
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.17
    0.28
    111
    +0.17
    0.24
    71
    +0.14
    0.26
    Negative Logits
    ³
    -4.85
    ¿½
    -4.84
    ij
    -4.75
    «
    -4.72
    ĻĤ
    -4.71
    ª
    -4.46
    ¬
    -4.42
    ↵
    -4.41
    -4.41
    -4.41
    POSITIVE LOGITS
    iterator
    1.61
    lessly
    1.56
     AFFIRMED
    1.55
    oscopy
    1.46
    ="\
    1.42
    appings
    1.40
    onuclear
    1.39
     preceded
    1.35
    tons
    1.33
    ÅĽÄĩ
    1.31
    Activations Density 5.876%

    No Known Activations