© 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 EvalsExportsinterp-engineNEWAPI 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. 24982
    Prev
    Next
    INDEX
    Explanations

    the article "The" used 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/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
    498
    +0.11
    0.6%
    419
    +0.10
    0.6%
    282
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.11
    0.01
    129
    +0.10
    0.01
    23
    +0.10
    0.01
    Negative Logits
    ĨĴ
    -1.98
    ¤
    -1.95
    ľĵ
    -1.88
    Ĥ¬
    -1.79
    ĻĤ
    -1.76
    »
    -1.68
    hao
    -1.65
    Īĺ
    -1.62
    ĥ½
    -1.58
    Ļª
    -1.56
    POSITIVE LOGITS
    !”
    2.20
     your
    1.67
    !’
    1.63
    !
    1.54
    ’
    1.50
    orbent
    1.42
    ”,
    1.40
     controls
    1.37
    )!
    1.37
     (,
    1.36
    Activations Density 0.004%

    No Known Activations