© 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. 24304
    Prev
    Next
    INDEX
    Explanations

    instances of section breaks or formatting indicators in the text

    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
    369
    +0.16
    0.9%
    410
    +0.15
    0.8%
    111
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.01
    91
    +0.15
    0.01
    298
    +0.15
    0.01
    Negative Logits
    ·¸
    -3.35
    £
    -2.94
    ij
    -2.86
      ↵
    -2.74
    -2.73
    Â
    -2.73
    ↵
    -2.73
    ↵
    -2.73
    ↵
    -2.73
     ↵
    -2.73
    POSITIVE LOGITS
    uvre
    1.66
    __.
    1.56
    __,
    1.55
    face
    1.52
    rors
    1.45
    êm
    1.42
    hurst
    1.41
    ('.
    1.41
    (".
    1.38
     essa
    1.36
    Activations Density 0.056%

    No Known Activations