© 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. 12310
    Prev
    Next
    INDEX
    Explanations

    instances of the article "the" in various contexts

    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
    98
    +0.17
    1.0%
    478
    +0.16
    0.9%
    476
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.17
    0.10
    291
    +0.16
    0.10
    98
    +0.16
    0.01
    Negative Logits
    coding
    -2.02
    agement
    -1.90
    atives
    -1.89
    guards
    -1.59
    standing
    -1.57
    ood
    -1.55
    iary
    -1.54
    ometry
    -1.54
    ative
    -1.52
    arial
    -1.51
    POSITIVE LOGITS
    4.11
    <|outofrange|>
    4.11
    4.11
    <|outofrange|>
    4.11
    ↵↵
    4.11
    č↵č↵
    4.11
    <|outofrange|>
    4.11
    4.11
    ↵↵
    4.11
    ↵  âĢĥ
    4.11
    Activations Density 0.788%

    No Known Activations