© 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. 2-RES-SM
    11. 14307
    Prev
    Next
    INDEX
    Explanations

    dates, times, and event details

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    198
    +0.22
    1.3%
    442
    +0.16
    1.0%
    235
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.22
    0.09
    198
    +0.16
    0.07
    220
    +0.12
    0.05
    Negative Logits
    ĥ½
    -3.94
    ²
    -3.77
    µ
    -3.70
    ³
    -3.63
      ↵
    -3.63
    -3.62
    <|outofrange|>
    -3.62
    -3.62
    ↵
    -3.62
    -3.62
    POSITIVE LOGITS
     onwards
    1.59
    iversary
    1.56
     anniversary
    1.53
    teenth
    1.48
     quarter
    1.44
    ivered
    1.41
     athlet
    1.40
     championships
    1.39
    holds
    1.38
     swords
    1.35
    Activations Density 1.169%

    No Known Activations