© 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. 29804
    Prev
    Next
    INDEX
    Explanations

    references to patient demographics and clinical study data

    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
    12
    +0.14
    0.8%
    73
    +0.11
    0.6%
    166
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.14
    0.04
    12
    +0.11
    0.02
    166
    +0.11
    0.03
    Negative Logits
     ...)
    -1.94
    Ħ
    -1.78
     etc
    -1.68
    fu
    -1.68
    ½
    -1.67
     ...,
    -1.63
     âĢ¦
    -1.54
     ”
    -1.54
     ...
    -1.51
     pi
    -1.49
    POSITIVE LOGITS
    umab
    1.60
    Theorem
    1.53
    oxylin
    1.52
    answered
    1.52
    compare
    1.51
    rieved
    1.50
    izumab
    1.47
    ena
    1.47
    nexpected
    1.45
     recorded
    1.44
    Activations Density 0.165%

    No Known Activations