© 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. 2-RES-SM
    11. 10222
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatment and patient characteristics

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    369
    +0.16
    0.9%
    207
    +0.15
    0.9%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.16
    0.05
    411
    +0.15
    0.04
    299
    +0.14
    0.04
    Negative Logits
     Redistributions
    -1.52
    distributed
    -1.43
     Words
    -1.41
    ToString
    -1.41
    breaker
    -1.39
     Used
    -1.37
     cookies
    -1.37
     ground
    -1.34
    ference
    -1.33
    /-/
    -1.32
    POSITIVE LOGITS
    Ļª
    3.06
    ĸ´
    2.76
    2.69
    2.69
    2.69
    ↵
    2.69
    <|outofrange|>
    2.68
    2.68
    ↵
    2.68
    ↵↵
    2.68
    Activations Density 0.712%

    No Known Activations