© 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 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. 10012
    Prev
    Next
    INDEX
    Explanations

    instances 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/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
    23
    +0.16
    0.9%
    489
    +0.15
    0.9%
    47
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.16
    0.06
    219
    +0.15
    0.06
    112
    +0.15
    0.05
    Negative Logits
    endor
    -1.86
    elist
    -1.82
    enda
    -1.76
    endas
    -1.72
    icorn
    -1.69
    opan
    -1.69
    itud
    -1.68
    olars
    -1.66
    oxifen
    -1.65
    notes
    -1.63
    POSITIVE LOGITS
    ...)
    2.35
    ¦
    2.21
    ?)
    2.19
    Īĺ
    2.18
     ).
    2.06
    ¯
    1.99
    ?).
    1.97
     ),
    1.89
    ĩ
    1.76
    Ľ
    1.72
    Activations Density 0.188%

    No Known Activations