© 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. 10441
    Prev
    Next
    INDEX
    Explanations

    elements related to health and safety regulations

    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
    156
    +0.18
    1.1%
    81
    +0.10
    0.6%
    269
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.18
    0.04
    410
    +0.10
    0.05
    73
    +0.10
    0.06
    Negative Logits
    ĵ
    -3.50
    ĨĴ
    -3.14
    IJ
    -2.90
    <|outofrange|>
    -2.86
    <|outofrange|>
    -2.86
    ↵
    -2.86
    č↵
    -2.86
    ↵
    -2.86
    -2.86
                ↵
    -2.86
    POSITIVE LOGITS
    udeau
    2.24
    uncher
    2.04
    ÅĦ
    2.03
    oka
    1.99
     Pradesh
    1.98
    uchy
    1.98
    Äĩ
    1.96
    Äij
    1.91
    uld
    1.91
    ção
    1.89
    Activations Density 0.514%

    No Known Activations