© 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. 1-RES-SM
    11. 24401
    Prev
    Next
    INDEX
    Explanations

    references to chronic conditions and diseases

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.20
    1.1%
    148
    +0.14
    0.8%
    327
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.20
    0.01
    343
    +0.14
    0.01
    468
    +0.13
    0.01
    Negative Logits
     suitable
    -1.61
     perfect
    -1.57
    illed
    -1.54
     different
    -1.49
     determined
    -1.48
     suprem
    -1.47
     definite
    -1.44
     precise
    -1.44
     appropriate
    -1.42
     particular
    -1.41
    POSITIVE LOGITS
    Ł
    3.62
    £
    3.55
    ·
    3.44
    º
    3.36
    ¼
    3.26
    ł
    3.24
    Ĩ
    3.22
    ¾
    3.21
    Īĺ
    3.10
    ij
    3.10
    Activations Density 0.030%

    No Known Activations