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

    Neuronpedia

    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. 11102
    Prev
    Next
    INDEX
    Explanations

    references to the name "Su" and its variations in context

    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
    369
    +0.16
    0.9%
    130
    +0.12
    0.7%
    393
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.04
    59
    +0.12
    0.03
    369
    +0.12
    0.01
    Negative Logits
    inib
    -2.01
    oscope
    -1.71
    lessly
    -1.66
    izumab
    -1.66
    off
    -1.66
    ingale
    -1.65
    wise
    -1.62
    matically
    -1.60
    otle
    -1.55
    reams
    -1.55
    POSITIVE LOGITS
    IJ
    3.81
    Ĭ
    3.65
    ½
    3.63
    µ
    3.53
    ·
    3.49
    Ŀ
    3.48
    ¬
    3.40
    Ľ
    3.40
    ĺ
    3.40
    Ĩ
    3.37
    Activations Density 0.196%

    No Known Activations