© 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. 15391
    Prev
    Next
    INDEX
    Explanations

    verbs related to labor or effort

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    337
    +0.19
    1.1%
    286
    +0.10
    0.6%
    28
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.19
    0.03
    15
    +0.10
    0.03
    429
    +0.10
    0.02
    Negative Logits
    Ĩ
    -2.29
    ī
    -2.01
    ĥ
    -2.00
    ¸
    -1.97
    ª
    -1.96
    Ħ
    -1.90
     times
    -1.87
    ľĵ
    -1.81
    ľ
    -1.77
    ģ
    -1.76
    POSITIVE LOGITS
     fine
    1.98
     through
    1.75
     on
    1.62
     backwards
    1.59
    around
    1.58
     async
    1.57
    example
    1.55
    through
    1.53
     with
    1.51
    estion
    1.50
    Activations Density 0.101%

    No Known Activations