© 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. 2-RES-SM
    11. 26309
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mathematical concepts and definitions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    17
    +0.17
    1.0%
    507
    +0.15
    0.8%
    181
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.17
    0.01
    207
    +0.15
    0.03
    212
    +0.14
    0.05
    Negative Logits
    Ŀ
    -2.06
    ģ
    -2.00
    Ĺ
    -1.95
    Ļª
    -1.92
    Į
    -1.89
    °
    -1.85
    ľĵ
    -1.82
    ±
    -1.81
    »¿
    -1.75
    ħ
    -1.75
    POSITIVE LOGITS
     itself
    1.57
     outfit
    1.55
     Club
    1.51
     Pradesh
    1.48
     Shop
    1.46
     Champions
    1.46
     Gym
    1.45
     Synd
    1.44
     [(\[
    1.44
     Stadium
    1.44
    Activations Density 0.614%

    No Known Activations