© 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. 24924
    Prev
    Next
    INDEX
    Explanations

    the name "Omer" as a recurring and prominent subject in the text

    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
    399
    +0.15
    0.8%
    272
    +0.11
    0.7%
    123
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.15
    0.01
    304
    +0.11
    0.01
    73
    +0.10
    0.01
    Negative Logits
     slightest
    -2.19
     least
    -1.77
     deny
    -1.59
     highest
    -1.55
    rapy
    -1.54
     slow
    -1.48
     delay
    -1.47
    rapeutic
    -1.46
    rolled
    -1.46
     mere
    -1.44
    POSITIVE LOGITS
    azine
    1.91
    ics
    1.88
    anges
    1.84
    ius
    1.81
    finder
    1.64
    cles
    1.64
    istry
    1.63
    Hint
    1.61
    naire
    1.59
    lique
    1.58
    Activations Density 0.111%

    No Known Activations