© 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. 9656
    Prev
    Next
    INDEX
    Explanations

    steps and ingredients related to cooking and food preparation

    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
    263
    +0.13
    0.7%
    172
    +0.12
    0.7%
    257
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.13
    0.05
    293
    +0.12
    0.06
    425
    +0.12
    0.06
    Negative Logits
    ']);
    -1.79
    ĥ½
    -1.72
    "],
    -1.67
    inher
    -1.65
    '];
    -1.65
    ...\
    -1.63
    '],
    -1.56
    Ī
    -1.56
    '=>
    -1.56
    ...](
    -1.56
    POSITIVE LOGITS
     bowl
    2.01
     moist
    1.77
    cco
    1.77
     baking
    1.77
     finish
    1.74
     ½
    1.72
     oven
    1.68
     gluten
    1.66
     heat
    1.65
     pasta
    1.65
    Activations Density 1.482%

    No Known Activations