© 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. 15127
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "is" and its variations in different 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/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
    307
    +0.18
    1.0%
    74
    +0.17
    0.9%
    57
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.18
    0.10
    23
    +0.17
    0.10
    83
    +0.14
    0.11
    Negative Logits
    ł
    -2.64
    ¯
    -2.60
    §
    -2.56
    ľĵ
    -2.46
    º
    -2.32
    ¬
    -2.32
    £
    -2.27
    »
    -2.24
    ¡
    -2.24
    Ł
    -2.23
    POSITIVE LOGITS
     amazing
    2.36
     unbelievable
    2.29
     imperative
    2.20
     incredible
    2.12
     sad
    2.04
     remarkable
    1.96
     ridiculous
    1.96
     stunning
    1.91
     definitely
    1.90
     scary
    1.89
    Activations Density 0.901%

    No Known Activations