© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30050
    Prev
    Next
    INDEX
    Explanations

    references to birth and related concepts

    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
    +0.14
    0.8%
    93
    +0.12
    0.7%
    397
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.14
    0.02
    389
    +0.12
    0.02
    38
    +0.11
    0.01
    Negative Logits
    ¯
    -3.01
    ĸ
    -2.60
    č↵
    -2.48
    ↵
    -2.48
    <|outofrange|>
    -2.48
    ↵
    -2.48
    -2.48
    ↵↵
    -2.48
    <|outofrange|>
    -2.48
              ↵
    -2.48
    POSITIVE LOGITS
     anniversary
    2.03
    sworth
    1.97
    place
    1.78
    rate
    1.75
    rates
    1.73
    hardt
    1.73
    bed
    1.71
    hart
    1.69
     rate
    1.68
    grounds
    1.66
    Activations Density 0.145%

    No Known Activations