© 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 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. 26386
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and punctuation marks in text

    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
    219
    +0.14
    0.8%
    215
    +0.13
    0.7%
    158
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.14
    0.00
    98
    +0.13
    0.00
    246
    +0.13
    0.00
    Negative Logits
    ĨĴ
    -2.28
      ↵
    -1.86
    ↵            ↵
    -1.85
    <|outofrange|>
    -1.85
    ↵
    -1.85
    -1.85
    <|outofrange|>
    -1.85
    <|outofrange|>
    -1.85
    -1.85
     ↵
    -1.85
    POSITIVE LOGITS
    ku
    1.57
    wide
    1.56
    way
    1.56
    piece
    1.54
    mas
    1.49
     guy
    1.48
    dess
    1.45
    ν
    1.42
    orte
    1.37
    ly
    1.37
    Activations Density 0.000%

    No Known Activations