© 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. 4-RES-SM
    11. 10091
    Prev
    Next
    INDEX
    Explanations

    references to oral treatments or therapies

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    158
    +0.13
    0.7%
    503
    +0.13
    0.7%
    18
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.13
    0.01
    195
    +0.13
    0.02
    18
    +0.11
    0.02
    Negative Logits
    point
    -1.58
    alus
    -1.58
    naments
    -1.55
    points
    -1.55
     unexpected
    -1.54
    quilibrium
    -1.51
    ikan
    -1.50
    bench
    -1.49
    ables
    -1.48
    ches
    -1.48
    POSITIVE LOGITS
    ¯
    2.49
     cavity
    2.13
     hygiene
    2.12
     contrace
    2.04
    dehyde
    1.99
     mucosa
    1.90
     delivery
    1.81
     bioavailability
    1.79
    ¿
    1.75
    ĻĤ
    1.71
    Activations Density 0.045%

    No Known Activations