© 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. 28910
    Prev
    Next
    INDEX
    Explanations

    phrases related to ordering and purchasing items

    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
    +0.17
    1.0%
    23
    +0.13
    0.7%
    56
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.17
    0.08
    376
    +0.13
    0.05
    358
    +0.13
    0.11
    Negative Logits
    Ł
    -4.87
    Ŀ
    -4.83
    £
    -4.72
    Ĵ
    -4.67
    §
    -4.63
    ı
    -4.62
    «
    -4.58
    ĸ
    -4.54
    ļ
    -4.53
    ŀ
    -4.53
    POSITIVE LOGITS
     lots
    1.81
     them
    1.80
     juices
    1.66
     plenty
    1.64
     craw
    1.64
     grocer
    1.64
     handy
    1.62
    oline
    1.58
     newspapers
    1.57
     customers
    1.55
    Activations Density 1.767%

    No Known Activations