© 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. 4-RES-SM
    11. 8628
    Prev
    Next
    INDEX
    Explanations

    numerical data points, particularly related to categorization or arrays

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    78
    +0.26
    1.8%
    397
    +0.20
    1.4%
    9
    +0.18
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.26
    0.10
    9
    +0.20
    0.10
    78
    +0.18
    0.02
    Negative Logits
    ically
    -1.30
    vas
    -1.26
    ament
    -1.25
    ques
    -1.21
    hold
    -1.19
    ships
    -1.16
    limits
    -1.15
    fe
    -1.14
     maxim
    -1.14
    verts
    -1.13
    POSITIVE LOGITS
    ļ
    2.16
    ŀ
    1.77
    ĵ
    1.77
    Ľ
    1.75
    İ
    1.72
    Ļ
    1.70
    Ķ
    1.66
    º
    1.64
    ı
    1.61
    Īĺ
    1.60
    Activations Density 0.570%

    No Known Activations