© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11987
    Prev
    Next
    INDEX
    Explanations

    information related to publications, authorship, and editorial roles

    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
    •probe features
    biographies, esp. for article authors

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    32
    +0.12
    0.7%
    233
    +0.11
    0.6%
    21
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.02
    34
    +0.11
    0.10
    450
    +0.11
    0.02
    Negative Logits
    ĸ´
    -2.77
    ł
    -2.75
    Īĺ
    -2.64
    ¯
    -2.59
    »¿
    -2.55
    ĸ
    -2.52
    ¢
    -2.46
    ļ
    -2.33
    Ļª
    -2.33
    Ģ
    -2.31
    POSITIVE LOGITS
     specializes
    2.33
     expertise
    2.28
     explores
    2.18
     freelance
    2.16
     author
    2.14
     focuses
    2.13
     insights
    2.12
     himself
    2.11
     enjoys
    2.05
     discusses
    2.05
    Activations Density 1.760%

    No Known Activations