© 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. 4-RES-SM
    11. 15231
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and performance metrics in engineering contexts

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    85
    +0.14
    0.8%
    9
    +0.14
    0.8%
    216
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.14
    0.05
    401
    +0.14
    0.03
    458
    +0.12
    0.02
    Negative Logits
    ¿
    -2.86
    ¼
    -2.70
    ĸ´
    -2.66
    Īĺ
    -2.64
    Ģ
    -2.62
    º
    -2.61
    Ĭ
    -2.60
    ·¸
    -2.58
    ¾
    -2.54
    ¥
    -2.51
    POSITIVE LOGITS
     thereof
    3.12
     xcex
    2.78
     therefrom
    2.62
    xe
    2.54
     thereto
    2.50
     thereon
    2.45
     hereinafter
    2.42
     therein
    2.40
     xe
    2.33
     thereby
    2.32
    Activations Density 0.420%

    No Known Activations