© 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 EvalsExportsAPI 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. 10378
    Prev
    Next
    INDEX
    Explanations

    ingredients and processes related to baking, particularly those that involve chocolate

    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
    156
    +0.18
    1.1%
    351
    +0.12
    0.7%
    56
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.18
    -0.00
    293
    +0.12
    0.03
    328
    +0.12
    0.04
    Negative Logits
    ·
    -2.23
    į
    -2.13
    ↵
    -2.11
    ↵  ↵
    -2.11
    -2.11
    ↵
    -2.11
    -2.11
             ↵
    -2.11
    ↵
    -2.11
    -2.11
    POSITIVE LOGITS
    makers
    2.21
    ulence
    1.98
    pack
    1.95
    nuts
    1.92
    beans
    1.90
    nut
    1.87
    handler
    1.85
    balls
    1.84
    pot
    1.81
     recipe
    1.78
    Activations Density 0.380%

    No Known Activations