© 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. 1-RES-SM
    11. 26179
    Prev
    Next
    INDEX
    Explanations

    references related to the Dalai Lama and Tibetan issues

    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
    350
    +0.17
    1.0%
    369
    +0.14
    0.8%
    296
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.10
    156
    +0.14
    0.07
    271
    +0.13
    0.01
    Negative Logits
    ureus
    -1.56
     helping
    -1.54
    unden
    -1.53
     hear
    -1.48
     ages
    -1.42
     directions
    -1.40
    edited
    -1.40
    paces
    -1.34
     subscrib
    -1.33
     insights
    -1.31
    POSITIVE LOGITS
    itto
    1.92
    OUBLE
    1.71
    yne
    1.71
    warf
    1.70
    sey
    1.64
    grass
    1.63
    uple
    1.57
    hedral
    1.55
    minster
    1.54
    olphin
    1.52
    Activations Density 0.614%

    No Known Activations