© 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 EvalsExportsAPI 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. 10779
    Prev
    Next
    INDEX
    Explanations

    medical terminology relating to congenital heart defects

    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
    21
    +0.18
    1.0%
    155
    +0.13
    0.8%
    30
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.18
    0.08
    30
    +0.13
    0.03
    155
    +0.13
    0.04
    Negative Logits
     theft
    -1.92
     raids
    -1.71
     pricing
    -1.68
     licenses
    -1.67
     competitive
    -1.65
     volatility
    -1.62
     promotions
    -1.61
     recipes
    -1.61
     marketing
    -1.59
     promotion
    -1.58
    POSITIVE LOGITS
    arynx
    2.47
     axis
    2.44
     quadrant
    2.43
     anterior
    2.38
     lobe
    2.37
     circumference
    2.33
     pelvis
    2.30
     periphery
    2.28
    iceps
    2.26
     abdomen
    2.24
    Activations Density 0.528%

    No Known Activations