© 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. 9752
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatment and health risks

    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
    307
    +0.33
    2.1%
    348
    +0.17
    1.1%
    466
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.33
    0.21
    306
    +0.17
    0.10
    466
    +0.16
    0.17
    Negative Logits
     pictured
    -1.28
     Photograph
    -1.28
     worth
    -1.27
     together
    -1.23
     titled
    -1.21
     named
    -1.16
    disambiguation
    -1.15
     puzzle
    -1.15
     whereby
    -1.14
     wherein
    -1.12
    POSITIVE LOGITS
    Īĺ
    3.66
    ↵
    3.64
    <|outofrange|>
    3.64
    3.64
    3.64
    3.64
    ↵
    3.64
    ↵↵
    3.64
    ↵
    3.64
    ↵
    3.64
    Activations Density 3.141%

    No Known Activations