© 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 EvalsExportsAPI 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. 27871
    Prev
    Next
    INDEX
    Explanations

    references to distractions and diverting attention

    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
    59
    +0.15
    0.9%
    156
    +0.14
    0.8%
    344
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.15
    0.06
    148
    +0.14
    0.03
    115
    +0.11
    0.03
    Negative Logits
    documentclass
    -1.91
     great
    -1.69
     wonders
    -1.56
    ports
    -1.55
    books
    -1.46
     guys
    -1.37
    places
    -1.36
     guts
    -1.36
     enormous
    -1.35
    mes
    -1.35
    POSITIVE LOGITS
    idone
    1.81
    ieux
    1.74
    uelle
    1.69
    ynamic
    1.63
    Ļª
    1.63
     warning
    1.59
    entary
    1.52
    ^\[[@
    1.45
     therefrom
    1.43
    icz
    1.42
    Activations Density 0.572%

    No Known Activations