© 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. 4-RES-SM
    11. 8923
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions in competitive sports or games

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.23
    1.4%
    306
    +0.19
    1.1%
    98
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.23
    0.04
    306
    +0.19
    0.04
    168
    +0.13
    0.05
    Negative Logits
    upt
    -1.55
    arily
    -1.48
     Redistributions
    -1.42
    reatment
    -1.39
     milling
    -1.38
     smelled
    -1.36
    ary
    -1.36
    cyst
    -1.36
    ergic
    -1.34
    irectory
    -1.33
    POSITIVE LOGITS
    ĥ½
    2.28
    ¯
    2.25
    ĸ´
    2.22
     rival
    2.20
    ½
    2.13
    Į
    2.13
    ²
    2.11
    °
    2.10
    Ī
    2.10
    ĵ
    2.07
    Activations Density 0.379%

    No Known Activations