© 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. 24065
    Prev
    Next
    INDEX
    Explanations

    terms that describe specific traits or features of objects or subjects

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.16
    0.9%
    148
    +0.15
    0.9%
    87
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.02
    148
    +0.15
    0.01
    156
    +0.13
    0.02
    Negative Logits
    uc
    -1.65
    hum
    -1.63
    arden
    -1.61
    hn
    -1.60
    iah
    -1.59
    «
    -1.58
    athon
    -1.57
    hav
    -1.56
    §
    -1.54
    ason
    -1.52
    POSITIVE LOGITS
     lines
    1.92
     curves
    1.88
     strengths
    1.86
     line
    1.79
    lines
    1.73
     flic
    1.65
     curve
    1.63
     gaps
    1.63
    osities
    1.58
     coronal
    1.57
    Activations Density 0.071%

    No Known Activations