© 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. 13959
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments

    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
    156
    +0.30
    1.7%
    98
    +0.17
    1.0%
    136
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    75
    +0.30
    0.04
    238
    +0.17
    0.03
    310
    +0.12
    0.03
    Negative Logits
    :`
    -1.68
    sizeof
    -1.65
    endor
    -1.60
     quantity
    -1.60
    åı·
    -1.57
    éĩı
    -1.56
    ostream
    -1.55
    ãĥ¼ãĤ¸
    -1.55
    ÅĽÄĩ
    -1.53
     width
    -1.49
    POSITIVE LOGITS
    Ļª
    3.15
    IJ
    2.77
    »¿
    2.76
    ĵ
    2.74
    ľĵ
    2.70
    ĥ
    2.57
    ĨĴ
    2.56
    ij
    2.48
    Ł
    2.39
    º
    2.37
    Activations Density 0.214%

    No Known Activations