© 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. 1-RES-SM
    11. 27893
    Prev
    Next
    INDEX
    Explanations

    references to steam and steam-related technologies

    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
    173
    +0.14
    0.9%
    156
    +0.14
    0.8%
    77
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.14
    0.02
    304
    +0.14
    0.01
    77
    +0.11
    0.01
    Negative Logits
    TRODUCTION
    -1.99
     favor
    -1.79
     entirety
    -1.72
     particular
    -1.71
     apologize
    -1.65
     hers
    -1.61
     pregnant
    -1.56
     obese
    -1.54
     focus
    -1.52
     vaccinated
    -1.52
    POSITIVE LOGITS
    bank
    1.86
    boat
    1.85
    pere
    1.85
    guns
    1.76
    mill
    1.74
    boats
    1.73
    bolt
    1.71
    rooms
    1.70
    mong
    1.66
    berg
    1.64
    Activations Density 0.158%

    No Known Activations