© 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. 32266
    Prev
    Next
    INDEX
    Explanations

    proper nouns associated with entities or companies

    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
    263
    +0.15
    0.9%
    141
    +0.13
    0.8%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.15
    0.00
    66
    +0.13
    0.14
    271
    +0.12
    -0.05
    Negative Logits
    ']))
    -1.35
     goodbye
    -1.34
    due
    -1.31
    activated
    -1.30
    inher
    -1.27
    '])
    -1.25
     commens
    -1.25
    planned
    -1.25
    ']);
    -1.23
    tig
    -1.22
    POSITIVE LOGITS
    ĭ
    2.20
    ¸
    2.20
    ĥ
    2.18
    Īĺ
    2.18
    ¼
    2.18
    Ļ
    2.07
    ·¸
    2.07
    ª
    2.06
    ↵
    2.06
    ↵
    2.06
    Activations Density 5.386%

    No Known Activations