© 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. 23841
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and player statistics

    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
    17
    +0.20
    1.1%
    156
    +0.13
    0.8%
    395
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    395
    +0.20
    0.08
    500
    +0.13
    0.12
    255
    +0.12
    0.06
    Negative Logits
     \[[@
    -1.85
     "*
    -1.70
     Pradesh
    -1.69
    derr
    -1.68
    .^[@
    -1.63
    \]).
    -1.58
    .[@
    -1.54
    \],
    -1.51
     ^[@
    -1.49
    bserver
    -1.49
    POSITIVE LOGITS
    ¼
    2.20
    Į
    1.93
    ´
    1.88
    ĵ
    1.84
    IJ
    1.82
    »
    1.79
    Ĭ
    1.75
    ĺ
    1.74
    Ļª
    1.73
    1.69
    Activations Density 6.903%

    No Known Activations