© 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. 12229
    Prev
    Next
    INDEX
    Explanations

    statistical data related to patient outcomes and clinical measurements

    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
    21
    +0.24
    1.4%
    156
    +0.14
    0.8%
    498
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.24
    0.06
    117
    +0.14
    0.07
    498
    +0.12
    0.07
    Negative Logits
    Ļ
    -4.38
    Ĥ
    -4.22
    ↵
    -4.21
    -4.21
    -4.21
             ↵
    -4.21
    ↵↵
    -4.21
    -4.21
    ↵
    -4.21
    -4.21
    POSITIVE LOGITS
     postoperatively
    2.31
     (âī¥
    2.25
     âī¥
    2.15
     (>
    2.06
     stratified
    2.05
     ranged
    2.03
     (%)
    1.99
     âī¤
    1.95
     +/-
    1.95
     were
    1.93
    Activations Density 0.783%

    No Known Activations