© 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. 31622
    Prev
    Next
    INDEX
    Explanations

    keywords related to event processing and task management in programming

    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
    156
    +0.34
    2.0%
    17
    +0.14
    0.8%
    484
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.34
    0.02
    484
    +0.14
    0.04
    99
    +0.12
    0.05
    Negative Logits
    ĥ½
    -2.87
    ·
    -2.86
    -2.67
    -2.67
    ↵
    -2.67
    -2.67
    -2.67
    ↵↵
    -2.67
    ↵
    -2.67
    <|outofrange|>
    -2.67
    POSITIVE LOGITS
    ?",
    2.08
    "?
    1.86
     #{
    1.84
     ?"
    1.72
    ↵
    1.68
    Args
    1.65
    .",
    1.64
     ."
    1.62
    ibernate
    1.62
     :)
    1.60
    Activations Density 0.438%

    No Known Activations