© 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. 11846
    Prev
    Next
    INDEX
    Explanations

    concepts related to philosophical ideas and debates

    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
    307
    +0.28
    1.6%
    466
    +0.17
    1.0%
    306
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.28
    0.21
    510
    +0.17
    0.21
    307
    +0.14
    0.19
    Negative Logits
     pic
    -2.04
    ubicin
    -1.82
     Photo
    -1.80
     zip
    -1.80
     jersey
    -1.78
     @
    -1.74
     (£
    -1.70
    .","
    -1.70
     phone
    -1.68
     filming
    -1.67
    POSITIVE LOGITS
     philosophers
    3.60
     epistem
    3.17
     philosopher
    3.11
     Heidegger
    3.07
     philosophical
    3.00
     Hegel
    2.99
     Aristotle
    2.95
     Nietzsche
    2.89
     metaphys
    2.89
     Philosoph
    2.78
    Activations Density 4.699%

    No Known Activations