© 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. 29318
    Prev
    Next
    INDEX
    Explanations

    questions seeking specific information or data

    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
    +0.13
    0.8%
    407
    +0.13
    0.8%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.13
    0.04
    407
    +0.13
    0.04
    13
    +0.12
    0.03
    Negative Logits
    ATION
    -1.67
    NAME
    -1.58
    OSS
    -1.56
    AGE
    -1.56
    msgstr
    -1.55
    inates
    -1.54
    tabs
    -1.51
    ermal
    -1.46
    -1.45
    itions
    -1.44
    POSITIVE LOGITS
     happened
    2.03
     cooks
    1.81
    cha
    1.63
    vu
    1.59
     else
    1.56
     cook
    1.48
    chu
    1.47
     fuss
    1.47
    hta
    1.46
    ching
    1.45
    Activations Density 0.088%

    No Known Activations