© 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. 14243
    Prev
    Next
    INDEX
    Explanations

    references to businesses and companies, particularly in the context of operations, challenges, and legal matters

    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
    156
    +0.30
    1.8%
    186
    +0.15
    0.9%
    311
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.30
    0.07
    186
    +0.15
    0.05
    311
    +0.12
    0.09
    Negative Logits
    jours
    -1.61
    etine
    -1.58
    али
    -1.54
    ала
    -1.54
    ftware
    -1.50
     marital
    -1.48
    edes
    -1.44
     autism
    -1.44
    ATES
    -1.44
     rue
    -1.42
    POSITIVE LOGITS
    wright
    1.59
    SEL
    1.52
     fixture
    1.49
    meter
    1.42
    weight
    1.41
     Plate
    1.36
     Engine
    1.33
    bone
    1.32
    holder
    1.31
    isor
    1.30
    Activations Density 1.230%

    No Known Activations