© 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. 30115
    Prev
    Next
    INDEX
    Explanations

    expressions of high quality or excellence

    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
    119
    +0.17
    1.0%
    477
    +0.12
    0.7%
    255
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.17
    0.06
    255
    +0.12
    0.05
    472
    +0.12
    0.04
    Negative Logits
    uelle
    -1.97
    isher
    -1.80
    ordan
    -1.72
    STRA
    -1.69
    ché
    -1.66
    YES
    -1.56
    DEX
    -1.53
    ISH
    -1.50
    FLAG
    -1.50
    OLOG
    -1.50
    POSITIVE LOGITS
    mouth
    1.79
    ifiable
    1.78
     luck
    1.65
     minds
    1.60
    ified
    1.60
     proportions
    1.58
     contributions
    1.57
    edly
    1.55
     prospects
    1.54
    fellow
    1.54
    Activations Density 0.117%

    No Known Activations