© 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. 24759
    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
    410
    +0.17
    1.0%
    478
    +0.17
    1.0%
    188
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.17
    0.10
    219
    +0.17
    0.08
    486
    +0.14
    0.07
    Negative Logits
    """
    -1.85
    ipro
    -1.54
    printf
    -1.49
    otomy
    -1.47
    eered
    -1.47
     \$
    -1.43
    ope
    -1.42
    irections
    -1.42
     roles
    -1.40
    opan
    -1.40
    POSITIVE LOGITS
    Īĺ
    2.32
    ?)
    2.28
    ´
    2.23
    ,)
    2.11
    Ĭ
    2.07
    ?).
    2.04
    Ľ
    1.99
    ī
    1.95
    disambiguation
    1.93
    ¦
    1.92
    Activations Density 0.261%

    No Known Activations