© 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. 30152
    Prev
    Next
    INDEX
    Explanations

    punctuated sentences or statements

    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
    368
    +0.12
    0.7%
    360
    +0.12
    0.6%
    419
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.10
    271
    +0.12
    0.05
    156
    +0.11
    0.04
    Negative Logits
     peroxidase
    -1.46
     Hers
    -1.43
    jee
    -1.41
     patented
    -1.37
    ½
    -1.35
    ply
    -1.33
    ves
    -1.32
     someday
    -1.31
     2020
    -1.31
     Nature
    -1.29
    POSITIVE LOGITS
    anese
    1.78
    ioned
    1.77
     Constit
    1.63
    ↵
    1.61
    itud
    1.57
    /-
    1.50
    uron
    1.42
    ""
    1.40
    ncia
    1.40
    eenth
    1.39
    Activations Density 0.032%

    No Known Activations