© 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. 4-RES-SM
    11. 9263
    Prev
    Next
    INDEX
    Explanations

    references to time spent engaging in activities or reflecting on life experiences

    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
    502
    +0.15
    0.9%
    78
    +0.15
    0.8%
    320
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.15
    0.07
    288
    +0.15
    0.07
    56
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -3.73
    Ģ
    -3.67
    ¼
    -3.63
    «
    -3.51
    Ħ
    -3.46
    ľ
    -3.41
    ı
    -3.34
    Ń
    -3.32
    Ŀ
    -3.32
    Ĭ
    -3.28
    POSITIVE LOGITS
     watching
    2.60
     researching
    2.57
     interviewing
    2.50
     observing
    2.48
     doing
    2.42
     figuring
    2.40
     discussing
    2.40
     exploring
    2.39
     talking
    2.37
     arguing
    2.36
    Activations Density 0.909%

    No Known Activations