© 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. 1-RES-SM
    11. 27125
    Prev
    Next
    INDEX
    Explanations

    equality signs or related symbols

    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
    478
    +0.17
    0.9%
    187
    +0.10
    0.6%
    357
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.17
    0.03
    131
    +0.10
    0.02
    490
    +0.10
    0.02
    Negative Logits
    HO
    -1.97
    \$
    -1.89
     \$
    -1.60
    places
    -1.55
     characterizing
    -1.50
    ously
    -1.48
    arily
    -1.45
    hift
    -1.45
     subspace
    -1.41
    amount
    -1.39
    POSITIVE LOGITS
    Ĭ
    1.89
    1.88
    1.88
    ↵
    1.88
    <|outofrange|>
    1.88
    1.88
    ↵
    1.88
    1.88
    ↵
    1.88
    1.88
    Activations Density 0.107%

    No Known Activations