© 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. 26087
    Prev
    Next
    INDEX
    Explanations

    terms related to production processes in various 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
    217
    +0.14
    0.8%
    156
    +0.13
    0.7%
    484
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.14
    0.02
    343
    +0.13
    0.02
    217
    +0.12
    0.02
    Negative Logits
    Ń
    -2.25
    ĥ½
    -2.14
    ĻĤ
    -1.98
    ¼
    -1.92
    unnumbered
    -1.84
    ŀ
    -1.82
    ij
    -1.80
    §
    -1.77
    ½
    -1.73
    £
    -1.68
    POSITIVE LOGITS
    manship
    1.94
     therefrom
    1.83
     jobs
    1.80
    ipeline
    1.71
     pipeline
    1.63
    Production
    1.63
     cents
    1.53
     venue
    1.52
    station
    1.52
     capacity
    1.51
    Activations Density 0.076%

    No Known Activations