© 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. 12363
    Prev
    Next
    INDEX
    Explanations

    requests or polite phrases asking for action or attention

    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
    129
    +0.14
    0.8%
    410
    +0.14
    0.8%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.14
    0.03
    390
    +0.14
    0.02
    129
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -3.96
    ↵
    -3.93
     ↵
    -3.93
    -3.93
    -3.93
    ↵
    -3.93
    -3.93
    -3.93
    ↵  ³³³
    -3.93
    -3.93
    POSITIVE LOGITS
     note
    2.18
    quez
    1.98
     pardon
    1.96
     replace
    1.71
     forgive
    1.67
     notice
    1.64
     Note
    1.62
     put
    1.59
     email
    1.56
     insert
    1.56
    Activations Density 0.089%

    No Known Activations