© 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 EvalsExportsAPI 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. 26440
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or ownership

    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
    23
    +0.39
    2.3%
    478
    +0.14
    0.8%
    8
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.39
    0.07
    304
    +0.14
    0.08
    23
    +0.11
    0.09
    Negative Logits
    ató
    -2.09
    liche
    -1.74
    fony
    -1.73
    ue
    -1.72
    ista
    -1.68
     heeft
    -1.62
    ização
    -1.62
    ime
    -1.57
    gage
    -1.57
    starter
    -1.57
    POSITIVE LOGITS
     extensive
    1.73
    cibly
    1.72
     great
    1.68
    ]{.
    1.67
     profound
    1.65
     subtle
    1.61
     specificity
    1.60
     hereditary
    1.60
     ancient
    1.58
     substantial
    1.58
    Activations Density 0.380%

    No Known Activations