© 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. 28013
    Prev
    Next
    INDEX
    Explanations

    references to medical professionals and situations involving healthcare

    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
    407
    +0.14
    0.8%
    434
    +0.12
    0.7%
    95
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.14
    0.02
    356
    +0.12
    0.02
    183
    +0.11
    0.02
    Negative Logits
    ivities
    -1.98
    ources
    -1.66
    adata
    -1.66
    istically
    -1.62
     anymore
    -1.61
    ize
    -1.58
    ivism
    -1.58
    icultural
    -1.56
     cultures
    -1.55
    ifle
    -1.55
    POSITIVE LOGITS
    suit
    1.63
     paper
    1.46
    ceeding
    1.41
    asone
    1.41
     favour
    1.39
     miracle
    1.34
    sheet
    1.34
    pton
    1.33
    lor
    1.31
    rating
    1.30
    Activations Density 0.067%

    No Known Activations