© 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. 30638
    Prev
    Next
    INDEX
    Explanations

    references to pancreatic cancer

    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
    410
    +0.13
    0.7%
    177
    +0.13
    0.7%
    203
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.13
    0.03
    386
    +0.13
    0.02
    410
    +0.12
    0.04
    Negative Logits
    documentclass
    -1.86
    eing
    -1.83
    boarding
    -1.67
    casting
    -1.61
    ");
    -1.58
    cology
    -1.57
    headed
    -1.53
    craft
    -1.48
    "));
    -1.47
    writing
    -1.46
    POSITIVE LOGITS
    hers
    2.01
    her
    1.97
    hes
    1.92
    kered
    1.92
    innati
    1.86
    ourt
    1.82
    arthy
    1.75
    heng
    1.72
    herin
    1.71
    hern
    1.68
    Activations Density 0.215%

    No Known Activations