© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27082
    Prev
    Next
    INDEX
    Explanations

    references to the name "Stephen" in various 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
    211
    +0.17
    0.9%
    156
    +0.16
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.17
    0.03
    43
    +0.16
    0.03
    385
    +0.14
    0.02
    Negative Logits
    osta
    -1.55
     yourself
    -1.52
    uscular
    -1.45
    WARE
    -1.45
    ceptor
    -1.41
     '')
    -1.40
    "?"
    -1.39
    idence
    -1.38
    ubot
    -1.36
     particular
    -1.35
    POSITIVE LOGITS
    son
    2.06
    stein
    2.00
    chitz
    1.99
     Curry
    1.72
    stown
    1.70
    pson
    1.70
    escence
    1.67
    ski
    1.67
     Hubble
    1.66
    thood
    1.62
    Activations Density 0.146%

    No Known Activations