© 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. 26058
    Prev
    Next
    INDEX
    Explanations

    terms related to malaria and its associated biological aspects

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.17
    1.0%
    304
    +0.13
    0.8%
    71
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.17
    0.03
    321
    +0.13
    0.03
    52
    +0.13
    0.01
    Negative Logits
    ĥ½
    -2.28
    ®
    -2.17
    ¬
    -2.15
    Īĺ
    -2.11
    Į
    -1.96
    °
    -1.96
    ij
    -1.88
    §
    -1.87
    «
    -1.83
    İ
    -1.81
    POSITIVE LOGITS
    bane
    1.99
     against
    1.98
    borne
    1.93
     species
    1.77
     outbreaks
    1.66
     larvae
    1.64
     infections
    1.62
    optera
    1.61
     spp
    1.59
    forest
    1.58
    Activations Density 0.186%

    No Known Activations