© 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. 23961
    Prev
    Next
    INDEX
    Explanations

    locations and terms related to natural phenomena and environmental contexts

    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
    369
    +0.18
    1.1%
    98
    +0.18
    1.0%
    217
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.18
    0.08
    217
    +0.18
    0.10
    222
    +0.13
    0.10
    Negative Logits
    ↵
    -2.67
    ↵            ↵
    -2.67
    -2.67
    -2.67
    ↵
    -2.67
    ↵↵
    -2.67
    -2.67
    ↵
    -2.67
     ↵
    -2.67
    -2.67
    POSITIVE LOGITS
    ue
    1.72
    ña
    1.66
    osa
    1.61
    ké
    1.57
     firms
    1.56
     outwe
    1.56
     Bay
    1.53
    amento
    1.53
    orship
    1.50
    makers
    1.48
    Activations Density 2.130%

    No Known Activations