© 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. 29750
    Prev
    Next
    INDEX
    Explanations

    word patterns related to artistic elements or concepts

    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
    295
    +0.11
    0.6%
    346
    +0.11
    0.6%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.11
    0.02
    339
    +0.11
    0.03
    253
    +0.10
    0.04
    Negative Logits
    yz
    -1.59
    ortune
    -1.48
    otrophic
    -1.40
     tomato
    -1.36
    obuf
    -1.35
    otypical
    -1.34
    ACP
    -1.33
    itrile
    -1.33
     overex
    -1.32
    idone
    -1.32
    POSITIVE LOGITS
    ĻĤ
    1.89
    imir
    1.75
    iger
    1.74
    iga
    1.72
    andals
    1.66
    robe
    1.66
    arians
    1.58
    wart
    1.57
    ows
    1.57
    makers
    1.55
    Activations Density 0.303%

    No Known Activations