© 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. 8816
    Prev
    Next
    INDEX
    Explanations

    references to biological species and their classification

    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
    21
    +0.20
    1.1%
    271
    +0.12
    0.7%
    248
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.20
    0.02
    21
    +0.12
    0.02
    98
    +0.11
    0.01
    Negative Logits
     office
    -1.68
     dedicated
    -1.52
     responsibility
    -1.51
     organizers
    -1.51
     integral
    -1.50
    gage
    -1.49
    ership
    -1.44
    oelectric
    -1.44
     someday
    -1.44
     offices
    -1.42
    POSITIVE LOGITS
    ĻĤ
    4.67
    Ľ
    4.41
    ↵
    4.29
      ↵
    4.29
    čč
    4.29
    4.29
    <|outofrange|>
    4.29
    4.29
    <|outofrange|>
    4.29
    ↵
    4.29
    Activations Density 0.222%

    No Known Activations