© 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. 12641
    Prev
    Next
    INDEX
    Explanations

    terms related to cytogenetics and scientific analysis techniques

    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
    +0.20
    1.2%
    339
    +0.15
    0.8%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.20
    0.01
    221
    +0.15
    0.01
    148
    +0.12
    0.00
    Negative Logits
    veis
    -1.79
     else
    -1.61
     endless
    -1.61
    hend
    -1.58
    Inflater
    -1.50
    versed
    -1.49
    denly
    -1.48
    etheless
    -1.44
    fficients
    -1.43
     obligation
    -1.43
    POSITIVE LOGITS
    idine
    1.72
    anic
    1.71
    uric
    1.57
    ings
    1.54
    ups
    1.53
    omic
    1.51
    ome
    1.39
    atics
    1.38
    ogenetic
    1.35
     Wayne
    1.35
    Activations Density 0.054%

    No Known Activations