© 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. 4-RES-SM
    11. 9835
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mark."

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    138
    +0.11
    0.6%
    352
    +0.11
    0.6%
    499
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.11
    0.03
    369
    +0.11
    0.01
    193
    +0.11
    0.03
    Negative Logits
     raft
    -1.50
     province
    -1.46
     place
    -1.44
     commune
    -1.38
    ANCE
    -1.38
     power
    -1.37
    OURCES
    -1.36
    IDE
    -1.33
     instant
    -1.33
    ffic
    -1.31
    POSITIVE LOGITS
    ©
    2.89
    down
    2.66
    ¾
    2.63
    ®
    2.55
    Ļª
    2.53
    eting
    2.49
    iewicz
    2.43
    eters
    2.41
    edly
    2.40
    Į
    2.39
    Activations Density 0.198%

    No Known Activations