© 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. 23864
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    31
    +0.13
    0.7%
    418
    +0.12
    0.7%
    74
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.13
    0.01
    291
    +0.12
    0.00
    98
    +0.12
    0.00
    Negative Logits
    iste
    -1.69
    azard
    -1.56
    ony
    -1.56
    sterdam
    -1.49
    ature
    -1.46
     philosophy
    -1.46
     chance
    -1.45
    ety
    -1.44
    inar
    -1.43
    emic
    -1.43
    POSITIVE LOGITS
    reads
    1.76
    ª
    1.74
    ¥
    1.67
     annually
    1.60
    ľĵ
    1.54
    âĢĤ
    1.52
     READ
    1.45
    rex
    1.45
    >>>
    1.42
     copies
    1.40
    Activations Density 0.002%

    No Known Activations