© 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. 24660
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections between 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
    376
    +0.15
    0.9%
    478
    +0.14
    0.8%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.15
    0.03
    489
    +0.14
    0.03
    69
    +0.13
    0.03
    Negative Logits
    "}](#
    -1.75
    gium
    -1.54
     followed
    -1.50
     positioned
    -1.45
    uncher
    -1.45
    ator
    -1.44
    legged
    -1.44
     rendered
    -1.41
    IX
    -1.40
    gn
    -1.33
    POSITIVE LOGITS
     them
    2.32
     sexes
    2.20
     these
    2.08
    them
    2.01
    ĻĤ
    1.97
     States
    1.73
    elon
    1.56
    ships
    1.54
     extremes
    1.46
     states
    1.41
    Activations Density 0.057%

    No Known Activations