© 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. 28643
    Prev
    Next
    INDEX
    Explanations

    phrases related to loading processes or states

    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
    +0.15
    0.8%
    496
    +0.12
    0.7%
    19
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.05
    156
    +0.12
    0.03
    17
    +0.11
    0.02
    Negative Logits
    ľ
    -2.05
    ¿
    -2.04
    ĩ
    -2.02
    ĨĴ
    -1.99
    ¯
    -1.96
    ¨
    -1.95
    §
    -1.89
    ľĵ
    -1.88
    ĸ´
    -1.88
    ŀ
    -1.86
    POSITIVE LOGITS
    eners
    1.87
    loader
    1.80
    haus
    1.73
    control
    1.68
    strap
    1.67
    cloth
    1.60
    odge
    1.54
    ered
    1.53
    maker
    1.52
    eer
    1.51
    Activations Density 0.241%

    No Known Activations