© 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. 9746
    Prev
    Next
    INDEX
    Explanations

    medical conditions and their details in clinical reports

    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
    497
    +0.14
    0.8%
    126
    +0.13
    0.7%
    432
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.14
    0.05
    289
    +0.13
    0.02
    343
    +0.12
    0.04
    Negative Logits
     ensembles
    -1.87
    !).
    -1.79
    )?
    -1.78
     prizes
    -1.78
    ?**
    -1.77
     libraries
    -1.73
     yourselves
    -1.73
    "—
    -1.71
     universities
    -1.70
    iers
    -1.65
    POSITIVE LOGITS
    ĻĤ
    4.70
    ľĵ
    3.80
    ¼
    3.41
    ´
    3.35
    ¯
    3.33
    ŀ
    3.31
    ĥ½
    3.30
    Ī
    3.21
    »
    3.18
    ·
    3.17
    Activations Density 0.629%

    No Known Activations