© 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. 25812
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "Does."

    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
    +0.15
    0.9%
    376
    +0.14
    0.8%
    387
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.15
    0.03
    273
    +0.14
    0.02
    387
    +0.12
    0.02
    Negative Logits
    atics
    -1.89
    issance
    -1.87
    ivas
    -1.77
    ubert
    -1.76
     whom
    -1.75
     tracks
    -1.75
    aja
    -1.75
    places
    -1.57
    vous
    -1.55
     shares
    -1.54
    POSITIVE LOGITS
    documentclass
    1.78
    nt
    1.77
    ox
    1.59
    xspace
    1.57
    opropyl
    1.55
    typeof
    1.54
    xymatrix
    1.52
    n
    1.49
    ercase
    1.49
    ocyan
    1.48
    Activations Density 0.073%

    No Known Activations