© 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. 13931
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and associated timelines

    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
    397
    +0.19
    1.1%
    299
    +0.12
    0.7%
    15
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    256
    +0.19
    0.07
    287
    +0.12
    0.08
    211
    +0.10
    0.08
    Negative Logits
    Ļ
    -5.39
    ·¸
    -5.29
    ĻĤ
    -5.16
    Ļª
    -5.13
    ³
    -5.04
    Ń
    -4.96
    ¿½
    -4.94
    Ĵ
    -4.81
    -4.78
    ↵
    -4.78
    POSITIVE LOGITS
     onset
    2.63
     initiation
    2.39
     began
    2.15
     begins
    2.07
     period
    2.03
     session
    2.01
     commenced
    2.00
     commencement
    1.96
     surgery
    1.94
     season
    1.92
    Activations Density 1.074%

    No Known Activations