© 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. 2-RES-SM
    11. 10601
    Prev
    Next
    INDEX
    Explanations

    references to various fields or areas of study

    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
    510
    +0.11
    0.6%
    100
    +0.10
    0.6%
    377
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.11
    0.02
    8
    +0.10
    0.01
    389
    +0.10
    0.02
    Negative Logits
    woke
    -1.66
    OOGLE
    -1.65
    dule
    -1.61
    ¿
    -1.61
     welcome
    -1.59
     happy
    -1.52
     congen
    -1.44
    )](#
    -1.41
    unnumbered
    -1.37
    tah
    -1.36
    POSITIVE LOGITS
    work
    2.41
    notes
    1.81
    workers
    1.75
    points
    1.74
    yard
    1.72
    med
    1.70
    iento
    1.70
    ores
    1.69
    piece
    1.68
    sworth
    1.67
    Activations Density 0.090%

    No Known Activations