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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29914
    Prev
    Next
    INDEX
    Explanations

    elements related to dates and times

    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
    72
    +0.15
    0.9%
    419
    +0.13
    0.8%
    350
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.15
    0.07
    232
    +0.13
    0.11
    350
    +0.13
    0.09
    Negative Logits
    ↵
    -1.93
    ↵
    -1.75
    -1.75
    ↵
    -1.75
    ↵↵
    -1.75
    <|outofrange|>
    -1.75
    -1.75
    -1.75
    -1.75
    ↵↵
    -1.75
    POSITIVE LOGITS
    Conclusion
    1.66
     Times
    1.56
    INGTON
    1.53
     Honorable
    1.50
    MENT
    1.49
     Evening
    1.49
     times
    1.48
     0000000000000000000000000000000000
    1.46
    ’
    1.43
    ATIONS
    1.43
    Activations Density 1.995%

    No Known Activations