© 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. 25442
    Prev
    Next
    INDEX
    Explanations

    content related to names and acronyms associated with various organizations or individuals

    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
    335
    +0.14
    0.8%
    386
    +0.12
    0.7%
    81
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.03
    410
    +0.12
    0.04
    335
    +0.12
    0.03
    Negative Logits
    ctors
    -1.56
    coming
    -1.55
    comings
    -1.53
    ties
    -1.53
    ters
    -1.52
    oxacin
    -1.46
     knots
    -1.44
     courage
    -1.43
    terday
    -1.41
    ÑģÑĤÑĮ
    -1.41
    POSITIVE LOGITS
    ARD
    1.87
    raf
    1.84
    OOGLE
    1.82
    ophers
    1.62
    YPT
    1.61
    uda
    1.60
    ulf
    1.56
    reens
    1.55
    ISTER
    1.50
    ilda
    1.49
    Activations Density 0.200%

    No Known Activations