© 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. 24091
    Prev
    Next
    INDEX
    Explanations

    references to halls and places of significance or recognition

    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
    410
    +0.11
    0.6%
    115
    +0.10
    0.6%
    184
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.11
    0.01
    503
    +0.10
    0.01
    57
    +0.10
    0.01
    Negative Logits
    cha
    -1.80
    aeda
    -1.75
     vain
    -1.62
    epithelial
    -1.49
     thee
    -1.48
    WD
    -1.48
     utmost
    -1.48
    rian
    -1.47
     MSM
    -1.43
    enig
    -1.41
    POSITIVE LOGITS
    iday
    2.51
    ings
    2.27
    ways
    2.25
    rooms
    2.23
    owed
    2.12
    inki
    1.99
    igan
    1.95
    esy
    1.86
    marks
    1.83
    member
    1.82
    Activations Density 0.093%

    No Known Activations