© 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. 27144
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly commas

    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
    203
    +0.17
    1.0%
    372
    +0.13
    0.8%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.17
    0.09
    317
    +0.13
    0.06
    192
    +0.13
    0.05
    Negative Logits
    àµį
    -1.94
    à±ģ
    -1.89
    à¯į
    -1.61
    àµ
    -1.60
    ionage
    -1.58
    à±į
    -1.55
    ி
    -1.53
    apters
    -1.45
    áĢº
    -1.45
    à¯ģ
    -1.43
    POSITIVE LOGITS
    which
    1.85
    but
    1.69
     subd
    1.62
     inclusive
    1.59
     which
    1.56
     born
    1.56
    an
    1.55
    whose
    1.52
    000
    1.50
     któ
    1.50
    Activations Density 0.537%

    No Known Activations