© 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. 29994
    Prev
    Next
    INDEX
    Explanations

    the presence of terminators or punctuation marks

    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
    105
    +0.14
    0.7%
    487
    +0.13
    0.7%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.04
    271
    +0.13
    0.02
    156
    +0.12
    0.02
    Negative Logits
    eter
    -1.73
    urious
    -1.55
    meal
    -1.41
     occasion
    -1.37
    dez
    -1.36
    ered
    -1.34
     Include
    -1.33
     alike
    -1.31
    gradle
    -1.31
    indi
    -1.29
    POSITIVE LOGITS
    ŀ
    2.75
    Ŀ
    2.39
    ¥
    2.36
    ±
    2.20
    Ł
    2.12
    ij
    2.11
    ®
    2.09
    Ń
    2.09
    ĺ
    2.04
    ĭ
    2.02
    Activations Density 0.008%

    No Known Activations