© 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. 2-RES-SM
    11. 11177
    Prev
    Next
    INDEX
    Explanations

    references to ultraviolet (UV) light and its effects or applications

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.18
    1.0%
    458
    +0.11
    0.6%
    507
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.18
    0.01
    230
    +0.11
    0.01
    85
    +0.11
    0.01
    Negative Logits
     owners
    -1.78
    mates
    -1.77
     vomiting
    -1.73
    clusively
    -1.65
     stomach
    -1.59
     happier
    -1.56
     mysq
    -1.53
     hers
    -1.52
     mum
    -1.51
     '</
    -1.47
    POSITIVE LOGITS
    Ĵ
    2.23
    ®
    1.95
    BER
    1.85
    度
    1.83
    raviolet
    1.74
    DCs
    1.71
    NESS
    1.64
     rays
    1.62
    ITED
    1.62
     LEDs
    1.60
    Activations Density 0.133%

    No Known Activations