© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23838
    Prev
    Next
    INDEX
    Explanations

    XML schema definitions and related elements in structured data

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    502
    +0.14
    0.8%
    444
    +0.11
    0.6%
    13
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.02
    502
    +0.11
    0.02
    17
    +0.11
    0.01
    Negative Logits
    hip
    -1.68
     interest
    -1.61
     bored
    -1.57
    ship
    -1.56
     correct
    -1.50
     pleasure
    -1.47
    ere
    -1.46
    off
    -1.45
     flaw
    -1.45
     unfair
    -1.43
    POSITIVE LOGITS
    ¢
    2.33
    º
    2.17
    ª
    1.87
    «
    1.84
    £
    1.80
    ricular
    1.78
    mith
    1.73
    Ĵ
    1.71
    ström
    1.70
    "}](#
    1.68
    Activations Density 0.104%

    No Known Activations