© 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. 24736
    Prev
    Next
    INDEX
    Explanations

    terms related to foreign entities or aspects

    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
    156
    +0.20
    1.1%
    37
    +0.14
    0.8%
    487
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.20
    0.03
    487
    +0.14
    0.02
    283
    +0.13
    0.02
    Negative Logits
    lessly
    -1.83
     complete
    -1.68
    ably
    -1.61
     gentle
    -1.59
     plead
    -1.59
    kte
    -1.56
     gonna
    -1.45
     playful
    -1.44
     faint
    -1.44
     definite
    -1.43
    POSITIVE LOGITS
     nationals
    1.97
    icile
    1.78
    erals
    1.77
    castle
    1.73
     quarters
    1.70
    currency
    1.68
    actors
    1.66
    arters
    1.61
    Express
    1.58
    azione
    1.58
    Activations Density 0.123%

    No Known Activations