© 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. 30143
    Prev
    Next
    INDEX
    Explanations

    references to challenges or issues encountered in various 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/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
    468
    +0.12
    0.7%
    372
    +0.12
    0.7%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.12
    0.02
    503
    +0.12
    0.02
    352
    +0.11
    0.03
    Negative Logits
     feet
    -1.54
    ils
    -1.44
    illion
    -1.43
    µ
    -1.43
     taken
    -1.41
    ·¸
    -1.39
    ulum
    -1.38
    çois
    -1.38
    /-/
    -1.36
    iveau
    -1.36
    POSITIVE LOGITS
    unnumbered
    1.75
    uble
    1.73
     currents
    1.62
    ier
    1.58
    bound
    1.47
    ptin
    1.42
    lot
    1.39
    linger
    1.39
     wi
    1.39
    ICAL
    1.38
    Activations Density 0.174%

    No Known Activations