© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29687
    Prev
    Next
    INDEX
    Explanations

    references to quantitative metrics or magnitudes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    129
    +0.15
    0.8%
    287
    +0.11
    0.6%
    107
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.17
    156
    +0.11
    0.09
    271
    +0.11
    0.06
    Negative Logits
    ¼
    -2.07
    aliana
    -2.02
    ½
    -1.97
    uin
    -1.81
    ¸
    -1.76
    iamo
    -1.70
    lish
    -1.60
    Ģ
    -1.54
    inese
    -1.46
    ±
    -1.43
    POSITIVE LOGITS
    bral
    2.07
    []{
    1.60
     increases
    1.60
     perpendicular
    1.56
    eries
    1.56
    wise
    1.56
     elev
    1.45
     spikes
    1.45
     (>
    1.42
     (\~
    1.40
    Activations Density 0.524%

    No Known Activations