© 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. 1-RES-SM
    11. 27110
    Prev
    Next
    INDEX
    Explanations

    terms related to teeth and dental hygiene

    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
    404
    +0.16
    0.9%
    1
    +0.12
    0.7%
    18
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.16
    0.02
    352
    +0.12
    0.02
    58
    +0.12
    0.01
    Negative Logits
    ¿½
    -3.35
    Ĺ
    -3.27
    Īĺ
    -3.25
    ¬
    -3.18
    Ĥ
    -3.10
    ķ
    -3.07
    ĸ
    -3.02
    ²
    -2.94
    ¥
    -2.78
    Ĭ
    -2.74
    POSITIVE LOGITS
    rique
    1.76
    bay
    1.70
    ings
    1.69
    ière
    1.69
    ème
    1.67
    berries
    1.67
    nuts
    1.66
    nen
    1.63
    CoV
    1.62
    ée
    1.59
    Activations Density 0.094%

    No Known Activations