© 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. 31467
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions and inquiries

    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
    478
    +0.16
    0.9%
    390
    +0.14
    0.8%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.16
    0.06
    505
    +0.14
    0.06
    103
    +0.12
    0.06
    Negative Logits
    asek
    -1.88
    ership
    -1.84
    house
    -1.74
    ¿½
    -1.68
    ename
    -1.68
    bench
    -1.66
    points
    -1.52
    istance
    -1.52
    strap
    -1.51
    ôt
    -1.51
    POSITIVE LOGITS
     Wrong
    1.57
    rap
    1.55
    Yes
    1.51
     Surely
    1.50
    ![
    1.45
     Probably
    1.44
    olated
    1.43
     Then
    1.43
     Yes
    1.42
     ug
    1.40
    Activations Density 0.189%

    No Known Activations