© 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. 23797
    Prev
    Next
    INDEX
    Explanations

    constructs and components related to programming and configuration settings

    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
    156
    +0.19
    1.0%
    337
    +0.12
    0.6%
    477
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.19
    0.11
    388
    +0.12
    0.11
    204
    +0.11
    0.10
    Negative Logits
     leadership
    -1.80
    pson
    -1.66
    iella
    -1.64
     creditors
    -1.62
     County
    -1.51
     himself
    -1.51
    sburg
    -1.47
    zeit
    -1.42
     authority
    -1.42
     privately
    -1.40
    POSITIVE LOGITS
    >=
    1.65
    ëĭĪëĭ¤
    1.49
    xrightarrow
    1.48
    orems
    1.46
    ras
    1.41
    prove
    1.41
    ../../
    1.39
    ='
    1.39
    ~=
    1.38
    leftarrow
    1.38
    Activations Density 4.088%

    No Known Activations