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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29150
    Prev
    Next
    INDEX
    Explanations

    occurrences of parentheses in the text

    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
    188
    +0.18
    1.0%
    478
    +0.17
    1.0%
    23
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.17
    271
    +0.17
    0.06
    156
    +0.17
    0.10
    Negative Logits
    emis
    -1.68
     activities
    -1.63
    artan
    -1.56
    ivities
    -1.56
    atics
    -1.55
    neys
    -1.55
    ette
    -1.54
    ology
    -1.53
    ios
    -1.51
    enda
    -1.50
    POSITIVE LOGITS
    ...)
    2.37
    ?)
    2.31
    >=
    2.00
    ?).
    1.77
    example
    1.75
    ``
    1.74
    laughs
    1.70
     ).
    1.70
     ),
    1.68
    ))?
    1.67
    Activations Density 0.627%

    No Known Activations