© 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. 2-RES-SM
    11. 30787
    Prev
    Next
    INDEX
    Explanations

    phrases related to prevention and safety measures

    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
    186
    +0.13
    0.7%
    182
    +0.12
    0.7%
    101
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.13
    0.03
    510
    +0.12
    0.03
    182
    +0.11
    0.03
    Negative Logits
    Īĺ
    -2.80
    ĵ
    -2.61
    £
    -2.61
    ¬
    -2.56
    ³
    -2.52
    ħ
    -2.46
    °
    -2.45
    ±
    -2.40
    Ķ
    -2.36
    ĥ
    -2.34
    POSITIVE LOGITS
    umatic
    1.80
     erosion
    1.70
    aphyl
    1.69
     leakage
    1.65
     evaporation
    1.62
     duplication
    1.61
    agne
    1.60
     contamination
    1.56
    aggio
    1.55
     germination
    1.54
    Activations Density 0.170%

    No Known Activations