© 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. 30001
    Prev
    Next
    INDEX
    Explanations

    file types and structure in coding contexts

    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
    478
    +0.15
    0.8%
    115
    +0.14
    0.8%
    247
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.15
    0.02
    129
    +0.14
    0.01
    250
    +0.14
    0.03
    Negative Logits
    ĻĤ
    -1.77
    mente
    -1.73
    ·
    -1.63
    ¿½
    -1.61
    ®
    -1.55
    nee
    -1.49
    nal
    -1.46
    amente
    -1.46
    ¦
    -1.45
    Ł
    -1.44
    POSITIVE LOGITS
    àµį
    1.89
    àµ
    1.63
    LICENSE
    1.49
    acetic
    1.37
    brevi
    1.36
     circumstantial
    1.34
    efore
    1.33
    acetate
    1.32
     inadequate
    1.31
    eon
    1.30
    Activations Density 0.179%

    No Known Activations