© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13499
    Prev
    Next
    INDEX
    Explanations

    expressions of humor and lightheartedness

    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
    369
    +0.19
    1.1%
    263
    +0.15
    0.9%
    56
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.19
    0.06
    410
    +0.15
    0.18
    339
    +0.14
    0.07
    Negative Logits
    ĥ½
    -2.40
    Ļª
    -2.39
    »¿
    -2.37
    ĭ
    -2.26
    Ĥ¬
    -2.15
    ĩ
    -2.07
    ĵ
    -2.07
    ij
    -2.06
    į
    -2.05
    ļ
    -2.02
    POSITIVE LOGITS
     sake
    1.96
     dude
    1.71
     crap
    1.62
    ishly
    1.61
     ok
    1.58
     Anyway
    1.57
     PURPOSE
    1.56
    shit
    1.52
    Anyway
    1.52
     okay
    1.51
    Activations Density 5.093%

    No Known Activations