© 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. 25023
    Prev
    Next
    INDEX
    Explanations

    references to kitchens and kitchen-related features

    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
    +0.18
    1.0%
    173
    +0.12
    0.7%
    494
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.18
    0.03
    465
    +0.12
    0.03
    173
    +0.12
    0.03
    Negative Logits
    ĸ
    -2.29
    ĥ½
    -2.19
    ¯
    -2.15
    ł
    -2.15
    ¦
    -2.12
    č↵
    -2.10
    ↵
    -2.10
    <|padding|>
    -2.10
    ↵
    -2.10
    ↵
    -2.10
    POSITIVE LOGITS
    nuts
    1.99
     cabinets
    1.99
    ettes
    1.82
     cabinet
    1.74
    ware
    1.70
     arrangements
    1.66
     appliance
    1.61
    ette
    1.60
     layout
    1.58
     arrangement
    1.57
    Activations Density 0.193%

    No Known Activations