© 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. 23931
    Prev
    Next
    INDEX
    Explanations

    function definitions in programming code

    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
    96
    +0.15
    0.8%
    220
    +0.13
    0.7%
    295
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.15
    0.02
    220
    +0.13
    0.02
    73
    +0.13
    0.02
    Negative Logits
    place
    -1.69
    upon
    -1.58
    Location
    -1.50
    tons
    -1.50
    GB
    -1.48
     Province
    -1.46
     Channel
    -1.43
    Gate
    -1.42
    Street
    -1.41
    yes
    -1.39
    POSITIVE LOGITS
    erals
    1.96
    aries
    1.81
    eral
    1.65
    ning
    1.49
     laun
    1.46
    nell
    1.46
     counseling
    1.44
     apprent
    1.44
    ters
    1.44
     courts
    1.42
    Activations Density 0.089%

    No Known Activations