© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    words related to cake or baking

    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
    392
    +0.12
    0.7%
    11
    +0.12
    0.7%
    497
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.12
    0.03
    386
    +0.12
    0.01
    231
    +0.11
    0.02
    Negative Logits
    Ĭ
    -2.30
    ij
    -2.19
    ·
    -2.00
    £
    -1.99
    ¼
    -1.86
    Ī
    -1.73
    ¡
    -1.69
    delim
    -1.69
    ©
    -1.67
    Ń
    -1.67
    POSITIVE LOGITS
    bery
    1.85
    berry
    1.83
    àµį
    1.82
    manship
    1.81
    phrine
    1.81
    ños
    1.79
    boarding
    1.78
     opportunity
    1.70
    weather
    1.65
    ground
    1.64
    Activations Density 0.276%

    No Known Activations