© 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. 30135
    Prev
    Next
    INDEX
    Explanations

    words associated with names or terms

    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
    369
    +0.12
    0.7%
    403
    +0.12
    0.7%
    492
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.12
    0.04
    366
    +0.12
    0.03
    253
    +0.11
    0.04
    Negative Logits
    fections
    -1.57
    ionage
    -1.50
     self
    -1.43
     prey
    -1.40
     unity
    -1.35
     handy
    -1.34
    fection
    -1.34
     doom
    -1.32
    jection
    -1.30
     {}
    -1.30
    POSITIVE LOGITS
    burg
    1.64
    bourne
    1.62
    ieux
    1.61
    insula
    1.58
    ening
    1.56
    INGTON
    1.55
    brook
    1.55
    heed
    1.54
    ovsky
    1.54
    BIO
    1.52
    Activations Density 0.279%

    No Known Activations