© 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. 29861
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries indicated by the word "asked."

    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
    171
    +0.15
    0.8%
    271
    +0.11
    0.6%
    211
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.15
    0.01
    166
    +0.11
    0.01
    45
    +0.11
    0.01
    Negative Logits
    aster
    -1.54
     qubits
    -1.46
     studies
    -1.43
    alities
    -1.41
    ostatin
    -1.40
     ORDER
    -1.39
     PG
    -1.38
     VALUES
    -1.31
     applicant
    -1.30
    vate
    -1.29
    POSITIVE LOGITS
    ĸ
    4.22
    ¿½
    3.84
    Ĩ
    3.68
    <|padding|>
    3.55
    <|outofrange|>
    3.55
    ↵
    3.55
    ↵↵
    3.55
    ↵
    3.55
               ↵
    3.55
      ↵
    3.55
    Activations Density 0.020%

    No Known Activations