© 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. 24903
    Prev
    Next
    INDEX
    Explanations

    references to significant years in academic or scientific research contexts

    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
    327
    +0.10
    0.6%
    423
    +0.10
    0.5%
    51
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.10
    0.04
    51
    +0.10
    0.04
    423
    +0.10
    0.03
    Negative Logits
     today
    -1.78
     Tuesday
    -1.73
     tonight
    -1.66
     trouble
    -1.63
     Thursday
    -1.62
     behold
    -1.57
     Tall
    -1.57
     Monday
    -1.56
     centre
    -1.52
     now
    -1.52
    POSITIVE LOGITS
    izumab
    2.18
    icolor
    1.58
    uscript
    1.51
    ystem
    1.51
    iom
    1.50
    esian
    1.49
    afka
    1.49
    ocument
    1.48
    ermann
    1.48
    odel
    1.46
    Activations Density 0.185%

    No Known Activations