© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 29843
    Prev
    Next
    INDEX
    Explanations

    specific medical terms and references related to diagnoses and treatments

    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
    51
    +0.14
    0.8%
    363
    +0.12
    0.7%
    1
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    84
    +0.14
    0.01
    51
    +0.12
    0.01
    288
    +0.12
    0.01
    Negative Logits
    ```
    -1.37
     starters
    -1.36
    $]{}
    -1.35
    Simplify
    -1.35
     background
    -1.34
    }$]{}
    -1.33
    anium
    -1.31
    []{
    -1.30
    ró
    -1.30
     %{
    -1.28
    POSITIVE LOGITS
    ¿½
    2.20
    ½
    2.10
    ¸
    2.08
    ¾
    2.05
    ©
    2.02
    ·
    2.02
    Īĺ
    2.00
    ¥
    2.00
    Ļª
    1.86
    ĥ
    1.85
    Activations Density 0.081%

    No Known Activations