© 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. 15313
    Prev
    Next
    INDEX
    Explanations

    references to male individuals or characters

    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
    73
    +0.13
    0.7%
    442
    +0.13
    0.7%
    450
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.13
    0.10
    73
    +0.13
    0.11
    163
    +0.13
    0.08
    Negative Logits
    ↵
    -7.83
    ↵
    -7.83
    ↵
    -7.83
    -7.83
    ↵↵
    -7.83
    ↵
    -7.83
    -7.83
    -7.83
    ↵
    -7.83
    ↵
    -7.83
    POSITIVE LOGITS
     who
    3.34
     whom
    2.77
     whose
    2.75
     named
    2.63
    who
    2.48
     himself
    2.34
    iac
    2.32
    whose
    2.23
     seated
    2.17
    friends
    2.15
    Activations Density 1.256%

    No Known Activations