© 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. 23778
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or sequences

    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
    478
    +0.16
    0.9%
    111
    +0.14
    0.8%
    271
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.03
    271
    +0.14
    0.01
    310
    +0.12
    0.02
    Negative Logits
    hips
    -1.49
     Medicine
    -1.45
    ICE
    -1.44
    ovir
    -1.43
     Medic
    -1.43
    ģ
    -1.41
    ism
    -1.39
    aders
    -1.39
    ±
    -1.37
     Ves
    -1.35
    POSITIVE LOGITS
    opus
    1.74
     accus
    1.58
    orems
    1.58
    hookrightarrow
    1.54
    á½IJ
    1.52
    arynge
    1.43
    аÑģÑģ
    1.40
    ãģ¾ãģĽ
    1.39
    acm
    1.38
    NdEx
    1.35
    Activations Density 0.157%

    No Known Activations