© 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. 2-RES-SM
    11. 31509
    Prev
    Next
    INDEX
    Explanations

    references to "whole" as related to grains or food

    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
    78
    +0.14
    0.8%
    139
    +0.12
    0.6%
    448
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.14
    0.02
    448
    +0.12
    0.01
    214
    +0.11
    0.02
    Negative Logits
    ubicin
    -2.04
    án
    -1.75
    arers
    -1.73
    icing
    -1.68
    chers
    -1.66
     inhibitors
    -1.62
    aries
    -1.55
    iners
    -1.52
    ppers
    -1.52
    inate
    -1.47
    POSITIVE LOGITS
    hearted
    2.34
    meal
    2.27
    heart
    2.11
    stock
    2.01
    sheet
    1.94
    blown
    1.81
     grain
    1.71
    line
    1.60
     genome
    1.55
    how
    1.53
    Activations Density 0.058%

    No Known Activations