© 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. 26776
    Prev
    Next
    INDEX
    Explanations

    references to licenses or copyright information

    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
    222
    +0.12
    0.7%
    364
    +0.10
    0.6%
    293
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.12
    0.02
    341
    +0.10
    0.02
    364
    +0.10
    0.02
    Negative Logits
     starters
    -1.50
    hline
    -1.42
     scenes
    -1.40
    thead
    -1.38
    ulle
    -1.36
    kan
    -1.34
    acters
    -1.34
    oge
    -1.33
    ()[
    -1.32
    ites
    -1.32
    POSITIVE LOGITS
     influenza
    1.38
    ://
    1.37
    TRODUCTION
    1.33
    ]{.
    1.32
     strain
    1.28
     Vinc
    1.27
     Ãħ
    1.26
    avirus
    1.26
    THER
    1.24
     interferon
    1.24
    Activations Density 0.046%

    No Known Activations