© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27929
    Prev
    Next
    INDEX
    Explanations

    references to French culture and people

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    100
    +0.15
    0.8%
    410
    +0.14
    0.8%
    338
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.05
    393
    +0.14
    0.02
    168
    +0.12
    0.02
    Negative Logits
    ulative
    -1.73
    ased
    -1.66
     naught
    -1.55
     nothing
    -1.54
     TRUE
    -1.53
     healthy
    -1.49
     NULL
    -1.48
     FALSE
    -1.47
    ']);
    -1.46
    bs
    -1.43
    POSITIVE LOGITS
    mont
    2.05
    ville
    1.95
    oire
    1.89
    bourg
    1.86
    ICO
    1.78
    rette
    1.77
    mong
    1.76
    Į
    1.73
    lyn
    1.73
    bour
    1.70
    Activations Density 0.257%

    No Known Activations