© 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. 28002
    Prev
    Next
    INDEX
    Explanations

    references to electronic cigarettes

    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
    369
    +0.20
    1.1%
    215
    +0.12
    0.7%
    364
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.20
    0.04
    215
    +0.12
    0.04
    201
    +0.12
    0.04
    Negative Logits
    ĻĤ
    -1.89
    Ļª
    -1.69
    Į
    -1.63
    ancia
    -1.61
    erve
    -1.55
     obstruction
    -1.46
     necrosis
    -1.45
    erver
    -1.45
    ¼
    -1.43
     improvement
    -1.42
    POSITIVE LOGITS
    psilon
    2.46
    greg
    1.92
    ugen
    1.85
    uclidean
    1.76
    gress
    1.71
    asing
    1.66
    lementary
    1.60
    Sports
    1.59
    vey
    1.54
    bers
    1.53
    Activations Density 0.106%

    No Known Activations