© 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. 25414
    Prev
    Next
    INDEX
    Explanations

    references to nitric compounds or related terms in a biological or medical context

    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
    111
    +0.15
    0.9%
    369
    +0.13
    0.7%
    267
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.10
    271
    +0.13
    0.05
    156
    +0.12
    0.05
    Negative Logits
     succeeding
    -1.78
     else
    -1.58
     scholarship
    -1.55
    pecially
    -1.54
    wards
    -1.53
     hearing
    -1.49
     developing
    -1.49
     meeting
    -1.48
     carrying
    -1.47
     mercy
    -1.47
    POSITIVE LOGITS
    §
    3.92
    ¢
    3.83
    Ń
    3.78
    İ
    3.78
    ¥
    3.76
    ģ
    3.75
    ¬
    3.64
    º
    3.57
    £
    3.56
    ±
    3.55
    Activations Density 0.173%

    No Known Activations