© 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. 15244
    Prev
    Next
    INDEX
    Explanations

    terms associated with engine functionality and performance

    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
    189
    +0.14
    0.8%
    211
    +0.14
    0.8%
    173
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.14
    0.05
    173
    +0.14
    0.04
    211
    +0.13
    0.04
    Negative Logits
    Ŀ
    -1.91
    itism
    -1.71
    gov
    -1.63
    ¯
    -1.62
    ¶
    -1.62
    Ĥ¬
    -1.61
    izumab
    -1.58
    ureus
    -1.57
    aki
    -1.56
    §
    -1.56
    POSITIVE LOGITS
     engine
    2.26
     engines
    2.06
     fuel
    2.04
     combustion
    1.96
     mechanic
    1.87
     ignition
    1.86
    engine
    1.84
     diesel
    1.79
     torque
    1.76
     turbo
    1.76
    Activations Density 0.330%

    No Known Activations