© 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. 2-RES-SM
    11. 26720
    Prev
    Next
    INDEX
    Explanations

    terminology and references related to various diseases

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.14
    0.8%
    186
    +0.11
    0.6%
    348
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.14
    0.02
    61
    +0.11
    0.02
    155
    +0.11
    0.02
    Negative Logits
    IJ
    -2.31
    ı
    -1.97
    µ
    -1.95
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.90
    -1.86
    -1.86
    <|outofrange|>
    -1.86
    ↵↵
    -1.86
     ↵
    -1.86
    -1.86
    POSITIVE LOGITS
    scape
    2.35
     pathogenesis
    2.08
    break
    2.01
     severity
    1.96
    fall
    1.95
     onset
    1.82
    CoV
    1.80
     mellitus
    1.78
     outbreaks
    1.77
     outbreak
    1.71
    Activations Density 0.070%

    No Known Activations