© 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. 30007
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and concepts related to roots and powers

    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
    +0.18
    1.0%
    111
    +0.15
    0.9%
    157
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.18
    0.04
    379
    +0.15
    0.04
    350
    +0.12
    0.03
    Negative Logits
     ([*
    -1.66
     precaution
    -1.53
     exhibit
    -1.42
    âĢIJ
    -1.37
     cap
    -1.32
     variation
    -1.31
     artery
    -1.31
     arb
    -1.29
    forming
    -1.25
     sacrifice
    -1.25
    POSITIVE LOGITS
    yler
    1.86
    ureus
    1.58
    uben
    1.55
    ffield
    1.54
    alore
    1.53
     regards
    1.50
    TRODUCTION
    1.43
    smallmatrix
    1.43
    ãĥ³ãĥĪ
    1.42
    oko
    1.41
    Activations Density 0.120%

    No Known Activations