© 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. 29012
    Prev
    Next
    INDEX
    Explanations

    references to stadiums and arenas

    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%
    482
    +0.14
    0.8%
    247
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.05
    156
    +0.14
    0.04
    271
    +0.12
    0.01
    Negative Logits
    unnumbered
    -1.87
     recommend
    -1.53
    Ĥ
    -1.53
    ²
    -1.52
    §
    -1.47
     faith
    -1.47
    acetyl
    -1.45
     dich
    -1.45
    rogenic
    -1.43
     apply
    -1.43
    POSITIVE LOGITS
    gio
    2.06
    illery
    1.97
    inson
    1.95
     Stadium
    1.90
    yard
    1.81
    smen
    1.71
    aña
    1.64
    game
    1.62
    ect
    1.60
    yards
    1.59
    Activations Density 0.260%

    No Known Activations