© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 27439
    Prev
    Next
    INDEX
    Explanations

    elements related to legal and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    153
    +0.17
    1.0%
    23
    +0.14
    0.8%
    143
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    178
    +0.17
    0.11
    271
    +0.14
    -0.03
    231
    +0.13
    0.11
    Negative Logits
    ounced
    -1.40
    ↵³³
    -1.39
     critically
    -1.39
    ="_
    -1.37
    PB
    -1.33
    ijn
    -1.32
    >=
    -1.30
    illac
    -1.30
    ionale
    -1.29
    iom
    -1.23
    POSITIVE LOGITS
    ¿½
    2.22
    Īĺ
    2.14
    ī
    2.04
    Ł
    2.02
    º
    1.93
    ĭ
    1.90
    Ŀ
    1.87
    ĵ
    1.85
    ł
    1.85
    Ī
    1.81
    Activations Density 3.605%

    No Known Activations