© 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. 12332
    Prev
    Next
    INDEX
    Explanations

    mentions of life and exploration beyond Earth

    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
    professor

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.19
    1.1%
    87
    +0.16
    0.9%
    333
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.19
    0.05
    285
    +0.16
    0.12
    393
    +0.12
    0.02
    Negative Logits
    ¢
    -3.03
    ¦
    -2.54
    ¯
    -2.49
    ¥
    -2.36
    Ĺ
    -2.31
    ¿
    -2.30
    ¤
    -2.28
    ¹
    -2.27
    ©
    -2.27
    Ĥ¬
    -2.25
    POSITIVE LOGITS
     faculty
    3.87
     Professor
    3.63
     Faculty
    3.56
     university
    3.46
     professors
    3.43
    Professor
    3.40
     professor
    3.40
    doctoral
    3.29
     research
    3.29
     undergraduate
    3.29
    Activations Density 1.989%

    No Known Activations