© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29780
    Prev
    Next
    INDEX
    Explanations

    references to medications or treatments related to health 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    81
    +0.15
    0.9%
    450
    +0.13
    0.7%
    211
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.15
    0.01
    211
    +0.13
    0.01
    410
    +0.13
    0.02
    Negative Logits
    akin
    -1.68
     excess
    -1.63
     spite
    -1.52
     worst
    -1.45
    IRE
    -1.43
     nausea
    -1.42
    blogspot
    -1.41
     rare
    -1.40
    >$
    -1.38
    oit
    -1.38
    POSITIVE LOGITS
    doms
    1.97
    ings
    1.94
    :`
    1.81
    ongs
    1.74
    idone
    1.71
    hood
    1.71
    lings
    1.61
    dom
    1.60
    ICO
    1.55
    led
    1.54
    Activations Density 0.114%

    No Known Activations