© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11647
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to patient conditions

    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
    307
    +0.27
    1.6%
    306
    +0.16
    1.0%
    248
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.27
    0.05
    216
    +0.16
    0.05
    23
    +0.12
    0.04
    Negative Logits
    ).\
    -1.87
    !).
    -1.80
     libraries
    -1.59
    !),
    -1.52
     bounty
    -1.51
    ebook
    -1.51
     wonders
    -1.50
     cents
    -1.50
     fly
    -1.48
    )~
    -1.47
    POSITIVE LOGITS
     Patients
    3.21
    ĥ½
    3.00
    ĻĤ
    2.86
    ¯
    2.71
    »
    2.68
     Diagnosis
    2.67
    Patients
    2.65
    Ĺ
    2.55
    ij
    2.53
    ī
    2.50
    Activations Density 0.153%

    No Known Activations