© 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. 23994
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "X" followed by a number or character

    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
    130
    +0.16
    0.9%
    410
    +0.14
    0.8%
    81
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.16
    0.04
    388
    +0.14
    0.04
    81
    +0.12
    0.04
    Negative Logits
    ighting
    -1.98
    king
    -1.90
    itoring
    -1.82
    iencies
    -1.80
    itting
    -1.73
     continuation
    -1.69
    raining
    -1.69
    ollowing
    -1.58
    osures
    -1.56
    iginally
    -1.55
    POSITIVE LOGITS
    enos
    1.79
    edo
    1.70
    writer
    1.65
    ño
    1.65
     chromosome
    1.64
    GRAM
    1.62
    pert
    1.57
    ®
    1.55
    iang
    1.55
    BOX
    1.53
    Activations Density 0.131%

    No Known Activations