© 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. 25506
    Prev
    Next
    INDEX
    Explanations

    the word "sed" in various contexts related to sedation and sedative effects

    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
    25
    +0.14
    0.8%
    369
    +0.11
    0.6%
    371
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.14
    0.02
    2
    +0.11
    0.02
    371
    +0.11
    0.01
    Negative Logits
    rapeut
    -1.64
    seeing
    -1.63
    atal
    -1.53
    inher
    -1.49
     mate
    -1.47
     child
    -1.44
     appreciated
    -1.41
     malaria
    -1.40
    oint
    -1.40
     class
    -1.40
    POSITIVE LOGITS
    istar
    1.82
    ieux
    1.70
    smallcaps
    1.68
    º
    1.65
    iments
    1.64
    ceptible
    1.60
    entary
    1.58
    iment
    1.57
    uar
    1.55
    vendor
    1.54
    Activations Density 0.097%

    No Known Activations