© 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. 4-RES-SM
    11. 11889
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical regions or institutions related to sports and education

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    82
    +0.14
    0.8%
    246
    +0.14
    0.8%
    438
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.14
    0.02
    82
    +0.14
    0.03
    98
    +0.13
    0.01
    Negative Logits
    ľĵ
    -2.79
    į
    -2.70
    Ĭ
    -2.58
    Ļª
    -2.49
    Į
    -2.45
    Ļ
    -2.45
    ¼
    -2.44
    ĥ½
    -2.44
    Ĥ¬
    -2.38
    ģ
    -2.32
    POSITIVE LOGITS
     Europe
    2.01
     Reserve
    1.90
     Province
    1.86
     Railway
    1.86
     Union
    1.84
     Ontario
    1.84
     Kentucky
    1.77
    ized
    1.76
     Pacific
    1.75
     District
    1.72
    Activations Density 0.112%

    No Known Activations