© 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. 2-RES-SM
    11. 12532
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and player statistics

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    497
    +0.13
    0.7%
    170
    +0.11
    0.6%
    430
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.13
    0.06
    69
    +0.11
    0.06
    362
    +0.11
    0.05
    Negative Logits
    backs
    -1.83
    keit
    -1.61
    forth
    -1.60
    ateness
    -1.49
     Abuse
    -1.44
     beginning
    -1.39
     Release
    -1.39
     abuse
    -1.37
     topology
    -1.36
     bound
    -1.35
    POSITIVE LOGITS
    Ļª
    4.18
    Ĵ
    4.02
    £
    3.98
    Ī
    3.98
    ½
    3.94
    ↵
    3.82
    3.82
    3.82
    č↵
    3.82
    3.82
    Activations Density 0.484%

    No Known Activations