© 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. 2-RES-SM
    11. 27607
    Prev
    Next
    INDEX
    Explanations

    numerical values and time-related phrases

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    294
    +0.18
    1.0%
    499
    +0.13
    0.7%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.18
    0.05
    326
    +0.13
    0.03
    292
    +0.11
    0.06
    Negative Logits
    ureus
    -1.85
     hearts
    -1.73
    )](#
    -1.57
    upon
    -1.55
    bies
    -1.54
    ettes
    -1.53
     playoffs
    -1.52
    DEX
    -1.50
     lists
    -1.49
    anguage
    -1.48
    POSITIVE LOGITS
     worth
    1.63
    coming
    1.56
     stranger
    1.39
    xit
    1.37
     saved
    1.32
    world
    1.31
    possible
    1.30
     missed
    1.30
    tagged
    1.29
    grad
    1.28
    Activations Density 1.382%

    No Known Activations