© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    references to children and adolescents in various contexts

    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
    186
    +0.17
    0.9%
    502
    +0.12
    0.7%
    75
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.17
    0.04
    406
    +0.12
    0.02
    359
    +0.12
    0.03
    Negative Logits
    Ļ
    -2.79
    ¿
    -2.67
    ↵
    -2.61
    ↵↵
    -2.61
     ↵
    -2.61
    č↵
    -2.61
    -2.61
    -2.61
     ↵
    -2.61
    ↵↵
    -2.61
    POSITIVE LOGITS
     ages
    2.83
     aged
    2.49
     born
    2.48
    birth
    2.43
    acing
    2.13
     attending
    2.10
     who
    2.07
    s
    2.07
     age
    2.03
     whose
    2.00
    Activations Density 0.125%

    No Known Activations