© 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. 23904
    Prev
    Next
    INDEX
    Explanations

    XML schema attributes related to Android layouts

    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
    27
    +0.15
    0.8%
    74
    +0.14
    0.8%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.15
    0.03
    74
    +0.14
    0.03
    54
    +0.12
    0.02
    Negative Logits
    ł
    -1.80
    ¼
    -1.78
    Ł
    -1.77
    ¿½
    -1.74
    erca
    -1.59
    ĻĤ
    -1.57
    ģ
    -1.56
    Ļ
    -1.55
    mouth
    -1.54
    hift
    -1.54
    POSITIVE LOGITS
    liche
    1.59
     forget
    1.57
    ibility
    1.51
    olester
    1.51
    oria
    1.49
    $–
    1.44
     incl
    1.41
     overest
    1.38
    >`
    1.37
    ache
    1.37
    Activations Density 0.090%

    No Known Activations