© 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. 13493
    Prev
    Next
    INDEX
    Explanations

    numerical values or calculations

    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
    464
    +0.11
    0.6%
    219
    +0.11
    0.6%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.11
    0.02
    438
    +0.11
    0.02
    219
    +0.11
    0.02
    Negative Logits
    imes
    -1.71
    ases
    -1.67
     plus
    -1.54
    agues
    -1.54
    ield
    -1.50
    ently
    -1.49
    enders
    -1.47
    inkle
    -1.42
    izations
    -1.41
    ancer
    -1.40
    POSITIVE LOGITS
    Ĥ¬
    2.15
    ¬
    2.13
    ¹
    2.07
    <|outofrange|>
    2.04
    <|outofrange|>
    2.04
    ↵
    2.04
    ↵↵↵
    2.04
    ↵↵↵
    2.04
    2.04
    č↵
    2.04
    Activations Density 0.089%

    No Known Activations