© 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. 29434
    Prev
    Next
    INDEX
    Explanations

    coding and programming-related terms, specifically namespaces

    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
    111
    +0.13
    0.8%
    507
    +0.11
    0.6%
    504
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.13
    0.02
    429
    +0.11
    0.02
    266
    +0.11
    0.02
    Negative Logits
     opportunity
    -1.40
     pellets
    -1.36
     attracting
    -1.35
    ptin
    -1.34
    tracks
    -1.33
    Statistical
    -1.29
     distinct
    -1.28
     pellet
    -1.28
     aggregate
    -1.28
     answer
    -1.25
    POSITIVE LOGITS
              ↵
    2.83
    ↵
    2.83
    <|outofrange|>
    2.83
    č↵
    2.83
    ↵
    2.83
    ↵
    2.83
    2.83
    ↵
    2.83
    ↵
    2.83
    ↵
    2.83
    Activations Density 0.032%

    No Known Activations