© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-SM
    11. 11588
    Prev
    Next
    INDEX
    Explanations

    terms related to patient outcomes and survival metrics in medical studies

    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
    332
    +0.11
    0.6%
    378
    +0.11
    0.6%
    291
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.11
    0.01
    149
    +0.11
    0.03
    482
    +0.11
    0.01
    Negative Logits
    »¿
    -3.42
    ½
    -2.62
    º
    -2.60
    «
    -2.51
    Īĺ
    -2.40
    ·¸
    -2.38
    ¼
    -2.33
    -2.31
    ↵
    -2.31
    -2.31
    POSITIVE LOGITS
     outcomes
    2.72
     rates
    2.61
     prognosis
    2.52
     outcome
    2.30
     scores
    2.16
     probabilities
    2.15
     rate
    2.09
     postoperatively
    2.08
     morbidity
    2.07
     statistics
    2.07
    Activations Density 0.171%

    No Known Activations