© 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. 4-RES-SM
    11. 11883
    Prev
    Next
    INDEX
    Explanations

    titles and headings in the document

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.23
    1.4%
    306
    +0.23
    1.3%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.23
    0.03
    347
    +0.23
    0.02
    296
    +0.12
    0.02
    Negative Logits
     thereof
    -1.94
     territory
    -1.59
     effort
    -1.57
     issue
    -1.52
    eur
    -1.50
     venture
    -1.49
    piration
    -1.47
    ously
    -1.43
     itself
    -1.42
    doms
    -1.42
    POSITIVE LOGITS
    ↵
    6.70
    <|outofrange|>
    6.70
    ↵
    6.70
    6.70
    6.70
     ↵
    6.70
    6.70
    ↵
    6.70
    6.70
    ↵
    6.70
    Activations Density 0.127%

    No Known Activations