© 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. 1-RES-SM
    11. 28221
    Prev
    Next
    INDEX
    Explanations

    references to allergies and allergic reactions

    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
    156
    +0.16
    0.9%
    492
    +0.11
    0.6%
    225
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.16
    0.01
    315
    +0.11
    0.01
    321
    +0.11
    0.01
    Negative Logits
    plit
    -1.54
    ano
    -1.52
    dale
    -1.52
     ago
    -1.50
     Univers
    -1.41
     corpor
    -1.41
    anova
    -1.39
     wasted
    -1.39
    yi
    -1.37
    git
    -1.37
    POSITIVE LOGITS
    Rs
    1.72
     reaction
    1.66
    atics
    1.61
     reactions
    1.53
     hypersensitivity
    1.52
    RI
    1.52
     traffic
    1.51
    raud
    1.51
    scape
    1.44
     triggers
    1.42
    Activations Density 0.083%

    No Known Activations