© 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. 2-RES-SM
    11. 32093
    Prev
    Next
    INDEX
    Explanations

    the word "that."

    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
    402
    +0.14
    0.8%
    23
    +0.14
    0.8%
    478
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.08
    401
    +0.14
    0.08
    434
    +0.13
    0.08
    Negative Logits
     alike
    -1.71
     forums
    -1.61
     presentations
    -1.58
    quin
    -1.43
     appearances
    -1.43
     forum
    -1.40
    aden
    -1.39
    bat
    -1.34
     consideration
    -1.34
     tournaments
    -1.34
    POSITIVE LOGITS
     happened
    1.70
     lasted
    1.68
    ¥
    1.65
     stray
    1.60
    ĥ½
    1.60
    ¼
    1.59
    ched
    1.54
    Ī
    1.48
    inny
    1.47
    ī
    1.44
    Activations Density 0.388%

    No Known Activations