© 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. 2-RES-SM
    11. 30790
    Prev
    Next
    INDEX
    Explanations

    topics related to healthcare and thyroid conditions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.34
    2.1%
    186
    +0.13
    0.8%
    240
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.34
    0.19
    71
    +0.13
    0.19
    111
    +0.13
    0.17
    Negative Logits
    ocyanate
    -1.85
    ano
    -1.65
    umar
    -1.57
    omitempty
    -1.53
    isel
    -1.52
    rophy
    -1.51
    pone
    -1.47
    scribe
    -1.47
    alc
    -1.45
    itzerland
    -1.45
    POSITIVE LOGITS
    doms
    1.71
    ]:
    1.67
    ):
    1.54
     divisions
    1.53
    yards
    1.52
     nations
    1.49
     establishments
    1.48
     seasons
    1.48
     institutions
    1.43
     histories
    1.43
    Activations Density 2.332%

    No Known Activations