© 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. 28637
    Prev
    Next
    INDEX
    Explanations

    constructs related to programming or software development

    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
    487
    +0.12
    0.6%
    322
    +0.11
    0.6%
    95
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    322
    +0.12
    0.12
    95
    +0.11
    0.14
    487
    +0.11
    0.10
    Negative Logits
      ↵
    -1.97
    ↵↵
    -1.97
    -1.97
    ↵  ↵
    -1.97
    <|outofrange|>
    -1.97
    <|outofrange|>
    -1.97
    ↵
    -1.97
    ↵↵
    -1.97
    ↵
    -1.97
        ↵
    -1.97
    POSITIVE LOGITS
    "}](#
    2.47
    !),
    2.01
    )',
    1.89
    )",
    1.86
    ),
    1.85
    ,)
    1.80
    ).)
    1.71
    ]),
    1.67
    )~
    1.66
    *),
    1.63
    Activations Density 5.571%

    No Known Activations