© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28057
    Prev
    Next
    INDEX
    Explanations

    words related to food or cooking

    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
    305
    +0.11
    0.6%
    170
    +0.11
    0.6%
    507
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.11
    0.02
    494
    +0.11
    0.01
    305
    +0.11
    0.01
    Negative Logits
    oshi
    -1.58
    pires
    -1.50
    atus
    -1.46
     "-
    -1.44
    icos
    -1.44
    ://
    -1.43
     Arabia
    -1.43
     deduction
    -1.41
    actic
    -1.41
    uttle
    -1.39
    POSITIVE LOGITS
    heid
    2.05
    ijn
    1.97
     organis
    1.88
    heer
    1.87
    elen
    1.74
     onder
    1.74
     invo
    1.71
     naar
    1.70
     geb
    1.69
    bund
    1.69
    Activations Density 0.123%

    No Known Activations