© 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. 2-RES-SM
    11. 14032
    Prev
    Next
    INDEX
    Explanations

    terms related to vaccines and immunological components

    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
    +0.20
    1.2%
    77
    +0.14
    0.8%
    497
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.20
    0.01
    446
    +0.14
    0.01
    271
    +0.11
    -0.00
    Negative Logits
    ĥ½
    -1.73
    IJ
    -1.64
     ende
    -1.63
     intend
    -1.59
    ŀ
    -1.57
    empre
    -1.57
     }).
    -1.55
     progress
    -1.55
     fprintf
    -1.55
    >()
    -1.54
    POSITIVE LOGITS
     antigens
    1.66
    arium
    1.59
     receptor
    1.58
    omics
    1.56
     revealed
    1.56
    atics
    1.51
    avirus
    1.50
     receptors
    1.49
    ic
    1.48
    CSF
    1.47
    Activations Density 0.042%

    No Known Activations