© 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. 1-RES-SM
    11. 27897
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate methods or approaches related to health or medical procedures

    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
    263
    +0.14
    0.8%
    230
    +0.13
    0.8%
    295
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.09
    295
    +0.13
    0.06
    457
    +0.12
    0.07
    Negative Logits
    amount
    -1.61
     shear
    -1.50
     pend
    -1.48
     prol
    -1.46
     rebounds
    -1.44
    bourg
    -1.43
    mered
    -1.41
     Triton
    -1.41
    oft
    -1.40
     viscos
    -1.37
    POSITIVE LOGITS
    ¿½
    4.66
    ¼
    4.32
    ¦
    4.25
    ĵ
    4.24
    Ń
    4.24
    ½
    4.21
    «
    4.19
    ĸ´
    4.13
    ij
    4.12
    Ĥ¬
    4.11
    Activations Density 0.677%

    No Known Activations