© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27138
    Prev
    Next
    INDEX
    Explanations

    references to political events and competitions

    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
    397
    +0.15
    0.9%
    199
    +0.12
    0.7%
    501
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    428
    +0.15
    0.12
    5
    +0.12
    0.15
    108
    +0.11
    0.13
    Negative Logits
    icht
    -1.65
    opolys
    -1.64
    inement
    -1.57
    lint
    -1.52
    iform
    -1.50
    microorganisms
    -1.49
    limits
    -1.46
     accessed
    -1.44
    ental
    -1.43
     Resources
    -1.42
    POSITIVE LOGITS
    Ī
    1.99
     contest
    1.77
    ¾
    1.72
    Ĭ
    1.64
     winning
    1.62
     occasion
    1.61
     singles
    1.58
     contests
    1.56
    ĭ
    1.54
     victory
    1.53
    Activations Density 1.670%

    No Known Activations