© 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. 29297
    Prev
    Next
    INDEX
    Explanations

    sentences that start with the phrase "There is."

    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
    23
    +0.15
    0.8%
    369
    +0.12
    0.7%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.15
    0.06
    121
    +0.12
    0.05
    216
    +0.11
    0.05
    Negative Logits
    greg
    -1.61
     (%)
    -1.56
    emporary
    -1.56
    2018
    -1.54
    ulates
    -1.50
    eries
    -1.47
    ubuntu
    -1.45
    mas
    -1.44
    audi
    -1.42
    ubernetes
    -1.41
    POSITIVE LOGITS
    ¦
    2.66
    ª
    2.65
    ↵
    2.39
    2.39
    2.39
    2.39
    ↵
    2.39
    <|outofrange|>
    2.39
     ↵
    2.39
    ↵↵
    2.39
    Activations Density 0.141%

    No Known Activations