© 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. 27838
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to events or outcomes

    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
    23
    +0.22
    1.2%
    258
    +0.19
    1.1%
    478
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.22
    0.15
    23
    +0.19
    0.14
    203
    +0.17
    0.10
    Negative Logits
    "}](#
    -2.90
    nikov
    -1.75
    ystems
    -1.61
    orov
    -1.61
    buntu
    -1.59
    yrinth
    -1.54
    azine
    -1.50
    ilo
    -1.50
     upstream
    -1.49
    "],
    -1.45
    POSITIVE LOGITS
    ^)
    1.56
    xml
    1.55
    aspx
    1.52
    used
    1.50
    jpg
    1.48
     Both
    1.48
    ushed
    1.48
    com
    1.47
    1.47
    ly
    1.43
    Activations Density 1.324%

    No Known Activations