© 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. 23771
    Prev
    Next
    INDEX
    Explanations

    references to distinct system functionalities or software features

    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
    177
    +0.15
    0.8%
    473
    +0.13
    0.7%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.15
    0.03
    177
    +0.13
    0.02
    367
    +0.12
    0.03
    Negative Logits
     owe
    -1.68
    ĺ
    -1.68
    helf
    -1.68
    omething
    -1.67
    ÖĢ
    -1.66
    ĨĴ
    -1.61
    hores
    -1.60
    heet
    -1.58
    AVE
    -1.54
    erver
    -1.52
    POSITIVE LOGITS
    master
    1.89
    ulated
    1.87
    osity
    1.86
    ulations
    1.69
    less
    1.66
    aries
    1.63
    zilla
    1.61
    ttes
    1.60
    meal
    1.59
    ishing
    1.54
    Activations Density 0.132%

    No Known Activations