© 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. 1-RES-SM
    11. 29103
    Prev
    Next
    INDEX
    Explanations

    details about medical treatments and their costs

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    23
    +0.14
    0.8%
    199
    +0.13
    0.7%
    184
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.14
    0.07
    23
    +0.13
    0.08
    186
    +0.13
    -0.01
    Negative Logits
     footprint
    -1.84
    bum
    -1.74
     heights
    -1.69
     intersections
    -1.67
     silhou
    -1.62
    sight
    -1.54
     Telescope
    -1.54
    avirus
    -1.53
     footage
    -1.50
    edly
    -1.49
    POSITIVE LOGITS
     administration
    1.85
     prophylaxis
    1.79
     treatment
    1.75
     administering
    1.75
     therapy
    1.71
     chemotherapy
    1.70
     Administration
    1.61
    administration
    1.59
     either
    1.59
     choice
    1.57
    Activations Density 1.334%

    No Known Activations