© 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. 29976
    Prev
    Next
    INDEX
    Explanations

    references to documents

    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
    156
    +0.20
    1.2%
    490
    +0.13
    0.7%
    352
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.20
    0.02
    306
    +0.13
    0.02
    352
    +0.11
    0.02
    Negative Logits
    ĥ½
    -1.79
     luck
    -1.70
     sexes
    -1.55
     sudden
    -1.53
    ÑĤÑĮ
    -1.49
    Ĺ
    -1.48
    riton
    -1.47
     shoulders
    -1.45
    ened
    -1.42
    leep
    -1.42
    POSITIVE LOGITS
    ière
    1.98
    ocortic
    1.70
     mentions
    1.67
    ieux
    1.67
     documents
    1.65
    sworth
    1.65
    iary
    1.61
    aries
    1.61
    zilla
    1.60
    uscript
    1.59
    Activations Density 0.055%

    No Known Activations