© 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 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. 27799
    Prev
    Next
    INDEX
    Explanations

    information related to educational systems and childhood development

    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
    365
    +0.14
    0.8%
    23
    +0.14
    0.8%
    350
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.14
    0.03
    229
    +0.14
    0.02
    426
    +0.14
    0.03
    Negative Logits
    Īĺ
    -2.84
    Ŀ
    -2.68
    ĭ
    -2.54
    ·¸
    -2.53
    ı
    -2.42
    ¥
    -2.36
    Ł
    -2.36
    º
    -2.34
    ī
    -2.31
    Ī
    -2.29
    POSITIVE LOGITS
     mornings
    1.57
    uits
    1.54
     finally
    1.51
    icul
    1.49
     secondary
    1.46
     aside
    1.46
    oral
    1.45
     between
    1.42
     dawn
    1.42
     accent
    1.42
    Activations Density 0.222%

    No Known Activations