© 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. 26235
    Prev
    Next
    INDEX
    Explanations

    references to "All-Star" events or themes

    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
    281
    +0.14
    0.8%
    82
    +0.12
    0.7%
    492
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.14
    0.03
    82
    +0.12
    0.03
    443
    +0.11
    0.02
    Negative Logits
    ¯
    -2.20
    ¹
    -2.18
    ŀ
    -2.11
    ľĵ
    -2.10
    ĥ½
    -2.07
    ±
    -2.02
    ´
    -2.02
    ĸ´
    -2.00
    Ķ
    -2.00
    ¢
    -1.98
    POSITIVE LOGITS
    ows
    2.43
    owed
    2.40
    owing
    2.33
    iances
    2.28
    iance
    2.03
    ograft
    2.02
    erg
    2.02
    uded
    1.95
    ocation
    1.94
    ied
    1.93
    Activations Density 0.108%

    No Known Activations