© 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. 23977
    Prev
    Next
    INDEX
    Explanations

    occurrences of widgets in a programming context

    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
    156
    +0.13
    0.7%
    321
    +0.12
    0.7%
    272
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    272
    +0.13
    0.02
    17
    +0.12
    0.01
    321
    +0.12
    0.02
    Negative Logits
     spite
    -1.90
     overtime
    -1.62
     eternity
    -1.50
     suspicion
    -1.50
     certain
    -1.50
     certainty
    -1.49
     compliance
    -1.47
     refusal
    -1.46
     innocence
    -1.46
     hope
    -1.45
    POSITIVE LOGITS
    ¢
    2.94
    ¡
    2.82
    ĸ
    2.81
    ĻĤ
    2.67
    İ
    2.63
    ·¸
    2.58
    ĭ
    2.54
    µ
    2.52
    ²
    2.49
    Ĩ
    2.47
    Activations Density 0.174%

    No Known Activations