© 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. 4-RES-SM
    11. 11708
    Prev
    Next
    INDEX
    Explanations

    actions or roles of biological systems or entities

    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
    348
    +0.16
    0.9%
    352
    +0.14
    0.8%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.16
    0.02
    15
    +0.14
    0.03
    429
    +0.12
    0.02
    Negative Logits
    µ
    -2.21
    İ
    -2.00
    ¨
    -1.97
    ¹
    -1.77
    ĥ½
    -1.75
    ª
    -1.73
    opia
    -1.68
    ¡
    -1.67
    ·¸
    -1.66
    Ī
    -1.63
    POSITIVE LOGITS
     pivotal
    1.98
     crucial
    1.95
     important
    1.84
     roles
    1.81
     hav
    1.80
     synerg
    1.74
     causative
    1.72
     vital
    1.67
     tricks
    1.61
    edly
    1.56
    Activations Density 0.099%

    No Known Activations