© 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. 29528
    Prev
    Next
    INDEX
    Explanations

    instances of the word "In."

    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
    +0.33
    2.0%
    478
    +0.21
    1.3%
    243
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.33
    0.09
    139
    +0.21
    0.07
    502
    +0.17
    0.07
    Negative Logits
    ours
    -1.85
    emic
    -1.83
    rails
    -1.77
    cias
    -1.73
    ungen
    -1.69
     (,
    -1.63
    nuts
    -1.59
    ender
    -1.58
    edly
    -1.58
    mage
    -1.57
    POSITIVE LOGITS
    ¿½
    3.86
    3.43
    ↵
    3.43
    3.43
    ↵
    3.43
    č↵č↵
    3.43
    ↵
    3.43
    č↵
    3.43
    č↵
    3.43
    ↵↵
    3.43
    Activations Density 0.238%

    No Known Activations