© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27124
    Prev
    Next
    INDEX
    Explanations

    method-related terms in programming or code documentation

    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
    431
    +0.16
    0.9%
    509
    +0.13
    0.7%
    454
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.16
    0.02
    509
    +0.13
    0.02
    391
    +0.13
    0.02
    Negative Logits
    ]>
    -1.78
    hin
    -1.74
    cher
    -1.69
     chick
    -1.61
     happier
    -1.56
    chitz
    -1.53
    coming
    -1.49
    cens
    -1.49
    7554
    -1.47
     whales
    -1.47
    POSITIVE LOGITS
    ology
    2.34
    ologic
    2.08
    ological
    2.01
    emaker
    1.87
    ista
    1.84
    nel
    1.83
    mage
    1.78
    ists
    1.76
    istas
    1.75
    naire
    1.75
    Activations Density 0.092%

    No Known Activations